404
+ +Page not found
+ + +diff --git a/.nojekyll b/.nojekyll new file mode 100644 index 0000000..e69de29 diff --git a/404.html b/404.html new file mode 100644 index 0000000..337d663 --- /dev/null +++ b/404.html @@ -0,0 +1,142 @@ + + +
+ + + + +Page not found
+ + +Based on this discussion in Discourse and our startup meeting, we can define an aerial autonomy stack as follows:
+++An aerial autonomy robotics stack is a collection of building blocks that enable the development of autonomous aerial vehicles, by providing a modular and scalable architecture for sensing, perception, planning, and control tasks. It allows unmanned aerial vehicles to perform complex missions without human intervention, while accommodating different hardware configurations and simulation environments.
+
From the paper
+++Fernandez-Cortizas, Miguel, et al. "Aerostack2: A Software Framework for Developing Multi-robot Aerial Systems." arXiv preprint arXiv:2303.18237 (2023).
+
the following autonomy stack table was extracted and adapted.
+Flight stack | +OS/OC | +Modular | +Tested in | +Middleware | +last update | +MF | +RO | +MA | +MP | +PO | +
---|---|---|---|---|---|---|---|---|---|---|
Aerostack | +✓ | +✓ | +S,RIL,ROL | +ROS | +10/2021 | +✗ | +✓ | +✓ | +✓ | +✗ | +
Aerostack2 | +✓ | +✓ | +S,RIL,ROL | +ROS 2 | +03/2023 | +✓ | +✓ | +✓ | +✓ | +✓ | +
AerialCore | +✓ | +✓ | +S,RIL,ROL | +ROS | +03/2023 | +✓ | +✓ | +✓ | +✗ | +✓ | +
Agilicious | +✓ | +✓ | +S,RIL | +ROS | +03/2023 | +✗ | +✓ | +✗ | +✗ | +✗ | +
KumarRobotics | +✓ | +✗ | +S,RIL,ROL | +ROS | +12/2022 | +✗ | +✓ | +✗ | +✓ | +✗ | +
CrazyChoir | +✓ | +✗ | +S,RIL | +ROS 2 | +02/2023 | +✗ | +✓ | +✓ | +✗ | +✗ | +
UAL | +✓ | +✗ | +S,RIL,ROL | +ROS | +12/2022 | +✓ | +✗ | +✗ | +✓ | +✗ | +
XTDrone | +✓ | +✓ | +S | +ROS | +03/2023 | +✗ | +✓ | +✗ | +✗ | +✗ | +
RotorS | +✓ | +✓ | +S | +ROS | +07/2021 | +✗ | +✓ | +✗ | +✗ | +✗ | +
GAAS | +✓ | +✓ | +S | +ROS | +10/2021 | +✗ | +✗ | +✗ | +✗ | +✗ | +
MRS AUV System | +✓ | +✓ | +S,RIL,ROL | +ROS | +09/2023 | +✓ | +✓ | +✓ | +✓ | +✗ | +
Crazyswarm | +✓ | +✗ | +S,RIL | +ROS | +12/2022 | +✗ | +✓ | +✓ | +✗ | +✗ | +
Crazyswarm2 | +✓ | +✓ | +S,RIL | +ROS 2 | +09/2023 | +✗ | +✓ | +✓ | +✗ | +✓ | +
Abbrivations +* OS/OC: Open source or Open code +* S: Experiments in simulation +* RIL: Experiments in the lab +* ROL: Experiments outside the lab +* MF: Multi-frame +* RO: Rate output +* MA: Multi agent +* MP: Multi platform +* PO: Plugin oriented
+Visual Inertial Odometry packages is an very important strategy of positioning within GPS deprived environments. Since UAVs can not use wheel odometry and heavily relient on cameras, this is one of the main drivers for autonomous exploration with these vehicles.
+Here is a list of VIO packages that people can use if they have a depth camera on their platform.
+This is just a list of autonomy stacks with links, such that later we can add them to the overview.
+Working list:
+A list of packages which don't comprise a full stack but do offer value on top of basic flight controller firmware.
+ +Given the above Aerial Autonomy Stacks, the list below outlines specific implementations of indoor navigation software packages in ROS, running on aerial vehicle platforms. The list, though not exhaustive, provides a good overview of available off-the-shelf non-commercial software.
+Package name | +OS/OC | +Sensors required | +Middleware | +Simulator | +Platform/controller | +Last updated | +
---|---|---|---|---|---|---|
Ardupilot ROS | +✓ | +LiDAR | +ROS 2 | +Gazebo | +Iris coptor,Ardupilot | +02/2024 | +
as2_behaviour_tree | +✓ | +Unknown | +ROS 2 | +Gazebo | +Crazyflie,DJI,Tello | +02/2024 | +
Teach-Repeat-Replan | +✓ | +Stereo camera | +ROS 1 | +MockaFly | +DJI N3 | +11/2020 | +
rtabmap | +✓ | +Stereo camera | +ROS 1 | +Gazebo | +PX4 | +05/2023 | +
ORB_SLAM_3 | +✓ | +Mono/stereo camera | +ROS 1 | +N/A | +Bebop 2 | +06/2023 | +
relative_nav | +✗ | +Stereo camera | +ROS 1 | +N/A | +Rotorcraft | +04/2017 | +
zephyr | +✓ | +LiDAR | +ROS 1 | +RotorS/Gazebo | +AscTec Firefly | +11/2018 | +
tum_ardrone | +✓ | +Mono camera | +ROS 1 | +N/A | +AR.Drone | +05/2014 | +
kr_autonomous_flight | +✓ | +Stereo camera/LiDAR/IMU | +ROS 1 | +Gazebo | +Pixhawk | +08/2023 | +
px4_sim_ros2 | +✓ | +Stereo camera | +ROS 2 | +Gazebo | +PX4 | +04/2024 | +
Usually, people tend to think about quadcopters when talking about aerial robotics, but there is actually a much larger variety of vehicle types available! Here's an attempt to list all of them if we can.
+Copters are aerial vehicles that use motors and propellers for their lift and maneuverability in 3D space.
+These usually are categorized into the following subcategories:
+Fixed-wing aerial vehicles use fixed wings for takeoff lift and control.
+These are the subcategories:
+Flapping-wing aerial vehicles generate both lift and thrust by their flapping wings.
+There are two main subcategories:
+Blimps or airships can also be used as aerial vehicles as well. These vehicles stay buoyant by using a balloon with lighter-than-air gas. Maneuverability is either done with flapping wings or rotors.
+Each autopilot suite have their a wide range of supported vehicles, to which this itemized list is referenced to. Note that these lists also include non-aerial vehicles as well.
+ + + +There are several autopilot suites available for control-boards for aerial vehicles. This page mostly have an overview of all of those including some comparison factors in them as well.
+Autopilot suite | +startup year | +latest version | +OS licence | +ROS support | +supported vehicles | +
---|---|---|---|---|---|
Ardupilot (GitHub) | +2009 | +4.5.2 (05/24) | +GPL 3.0 | +yes | +Copters, Fixed wings, VTOL | +
Betaflight (GitHub) | +2015 | +4.5.0 (04/24) | +GPL 3.0 | +no | +Copters | +
crazyflie-firmware (GitHub) | +2011 | +2024.2 | +GPL 3.0 | +yes* | +Quadcopters, Flapping wings | +
DJI autopilot (GitHub) | +2006 | +2023.9 | +closed | +yes | +Copters, VTOLS | +
Paparazzi (GitHub) | +2003 | +6.3.0 (12/23) | +GPL 2.0 | +no | +Copters, Fixed wings, VTOL | +
PX4 (GitHub) | +2009 | +1.14.0 (10/23) | +BSD 3-Clause | +yes | +Copters, Fixed wings, VTOL | +
ROSflight (GitHub) | +2019 | +2.2.0 beta (09/23) | +BSD 3-Clause | +yes | +Copters, fixed wings | +
*community provided support
+ + +This page will contain a list of education courses or tutorials for aerial robotics. +This is a partly compilation of this ROS discourse thread and the May meeting about tutorials and education and some googling :)
+This also includes input from a Linkedin post for a call of suggestions. This has been an adaption from the following Bitcraze Blogpost, and the overview presentation done for the ROS-aerial CWG meetings
+This section explains some of the recourses in more detail.
+There is this important resource which is the book titled ‘Small Unmanned Aircraft: Theory and Practice.’ This book has been written by Randy Beard and Tim McLain of Brigham Young University, and it covers everything from the absolute basics of coordinate frames and quadrotor dynamics to path planning and cameras. It is a must-read for anybody starting in UAVs and Aerial robotics.
+The physical book can be found here: http://press.princeton.edu/titles/9632.html
+The available PDFs can be accessed on GitHub: https://github.com/randybeard/uavbook
+This section shows online courses for aerial robotics with online instructor.
+Coursera offers the ‘Robotics: Aerial Robotics’ course as part of the Robotics specialization. Taught by Prof. Vijay Kumar from Penn University, this 4-week course covers the mechanics and control of aerial vehicles using Matlab. It starts from 1 dimension and gradually progresses to the 3rd dimension in simulation. The course is part of a paid educational program, but you can audit the lessons for free.
+Link: https://www.coursera.org/learn/robotics-flight
+Udacity has been offering a course on Aerial Vehicles for quite some time for the Flying car nano degree. The lessons are taught by top names in the industry and cover key aspects of Aerial Robotics, such as motion planning, controls, and estimation, with lab assignments involving a real drone. The course duration is 4 months, and access is available for a fee.
+Link: https://www.udacity.com/course/flying-car-nanodegree–nd787
+edX offers the 'ETHx: Autonomous Mobile Robots' course. Taught by Prof. Roland Siegwart, Dr. Davide Scaramuzza, Prof. Marco Hutter, Prof. Margarita Chli, Prof. Martin Rufli and Prof. Nicholas Lawrance from ETH Zurich, this 15-week course focuses on the principles of autonomous navigation and control of mobile robots. It covers topics such as perception, localization, planning, and control, which are essential for enabling robots to operate autonomously in dynamic environments. You can audit the course material for free with limited access.
+ +Additionally, there’s the course ‘Applied Control System 3: UAV Drone (3D Dynamics & Control)’ which is part of a series by Mark Misin. This course delves deep into the dynamics, control, and modeling of quadrotors.
+Link: https://www.udemy.com/course/applied-control-systems-for-engineers-2-uav-drone-control/
+This section showes university courses that have released recordings of lectures, slides and/or assignments. For instructions participants would need to follow the actual course at that one university.
+The University of Maryland offers a course on Autonomous Aerial Robotics, making all videos, slides, and assignments available. Taught by Nitin J. Sanket and Chahat Deep Singh, the course covers everything from basic control and dynamics to full autonomy. It’s a comprehensive resource for aerial robotics. The course utilizes the Parrot Bebop 2.0, and while a Mocap system is required, you may explore the possibility of adapting the course to a different platform. ROS is also part of this course
+Link: http://prg.cs.umd.edu/enae788m
+‘Visual Navigation For Autonomous Vehicles’ is a course available on MIT Open Courseware, taught by Prof. Luca Carlone. As the name implies, the course primarily focuses on autonomous navigation for any autonomous vehicle. It includes exercises where students implement vision algorithms on both ground robots and drones. Additionally, the course covers working with ROS and applying the knowledge to a simulated drone in Unity. The students also get to learn how to work with ROS
+Link: https://ocw.mit.edu/courses/16-485-visual-navigation-for-autonomous-vehicles-vnav-fall-2020/
+The ‘Bio-inspired Robotics’ course at the University of Washington, led by Prof. Sawyer Fuller, explores the realm of drawing inspiration from nature rather than reinventing the wheel. It covers various robots inspired by creatures capable of swimming, walking, hopping, and of course, flying. Lab assignments in this course involve working with a Crazyflie drone.
+Link: https://faculty.washington.edu/minster/bio_inspired_robotics/
+Brown University offers a course called ‘Introduction to Robotics’ taught by Prof. Stefanie Tellix. While the introduction covers generic robotics, the focus of the full course is on building and programming the Duckiedrone. The course dives straight into autonomy and also teaches students how to work with ROS.
+Link: https://cs.brown.edu/courses/cs1951r/
+Princeton University have also decided to release their ‘Intro to Robotics’ lectures and materials for the public. It covers all from control and estimation, computer vision and planning. Also it offers lab assignments with the Crazyflie.
+Link: https://irom-lab.princeton.edu/intro-to-robotics/
+Youtube also has quite some tutorials available so this section highlights a few.
+Drone Programming with Python: This popular tutorial/course teaches viewers how to program a real drone using Python with the DJI Tello. It offers a great opportunity for anyone looking for a short and enjoyable project to undertake, especially on a rainy day, while still working with a real platform.
+Link: https://youtu.be/LmEcyQnfpDA
+Intelligent Quads YouTube Channel: This channel is entirely dedicated to creating autonomous UAVs, covering topics from Ardupilot to MAVlink to ROS and Gazebo. It appears to be a valuable resource for beginners in the field of autonomous UAVs. This also includes ROS as part of the lessons as well.
+Link: https://www.youtube.com/@IntelligentQuads
+Here are some code examples that can be used as reference for experiments.
+Mambo ROS Examples: This is a collection of experiments targeted Parrot Mambo drones, there are experiments with one or multiple vehicles at the same time. It runs over ROS over BLE, and some test are adapted to make use of a Vicon MoCap system. From a control theory's perspective, it showcases an optional robust control strategy, using an H-Infinity controller with perturbation estimation and a identified dynamic model of a Parrot Mambo drone.
+Link: https://github.com/TOTON95/Mambo_ROS_Examples
+So here there are some courses that either doesn't fit in the above categories or are deprecated.
+This list contains some resources that we haven't included in the overview. Remove the item once it has been included
+Lots of thanks for anybody contributing to this linkedin post. This was extremely helpful!
+ + +This is an list of development platforms for aerial robotics. Please start a pull request if you'd like to update these.
+These are platforms that are currently commercially available for anybody to buy for their research.
+These are platforms that are standard within a lab or department, with information of what it contains provided with perhaps build instructions.,
+Many of the UAVs are usually built by hand and composed of different components. This usually consists of a drone frame, flight controller boards, companion computers and of course motors, batteries and ESCs.
+Many drone frames are usually built from carbon fiber and custom-made for application or research. +There are some frames that are provided that will provide some base: +- DJI Flame wheel ARF kit F550, F450, F330 +- Momentum Drones DEV-7
+For the drones that can carry it, the companion computers are important since they can do additional computations that the flight controller can not easily do. +As these are capable of running some form of Linux, these can handle for instance computer vision with OpenCV or run nodes with ROS. +Some companion computers also integrate flight control (RTOS) hardware in the same package
+Several vendors have developed carrier boards that can expose input/output ports of companion computers mentioned above which are packaged in a System-on-Module (SoM) form factor and also offer a standard interface for plugging in popular flight controllers/their own FCs.
+The Holybro S500v2 is a popular, relatively low-cost quadcopter. This is a list of the parts used with details of battery, motors, ESCs, and propellers with reference links to guide custom builds.
+S.No | +Part Name | +Part category | +Description | +Price (USD) | +Qty | +Total Cost (USD) | +Official/Reference Link | +
---|---|---|---|---|---|---|---|
1 | +Holybro S500 frame | +Frame | +With landing gear, 385x385mm | +42 | +1 | +42 | +https://holybro.com/collections/s500/products/s500-v2-kit?variant=42724497391805 | +
2 | +Holybro Pixhawk 6C + GPS + Power module | +FC + GPS + Power module | +PM02 power module, M9N GPS | +290 | +1 | +290 | +https://holybro.com/products/pixhawk-6c?variant=43005243785405 | +
3 | +Holybro 2216 920KV CW | +Motor | +19x19 mounting clockwise rotation | +20 | +2 | +40 | +https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094608061 | +
4 | +Holybro 2216 920KV CCW | +Motor | +19x19 mounting counter-clockwise rotation | +20 | +2 | +40 | +https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094640829 | +
5 | +BLHeli S 20A ESC | +ESC | +Electronic Speed Controller to drive motors | +14 | +4 | +56 | +https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094706365 | +
6 | +1045 propellers | +Props | +10x4.5" kit of 2 pairs | +12 | +1 | +12 | +https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094313149 | +
7 | +Radiomaster R81 receiver | +Radio receiver | +Used for manually flying drone Line of Sight/testing* | +18 | +1 | +18 | +https://holybro.com/products/radiomaster-r81-receiver | +
8 | +Holybro SiK telemetry radio v3 | +Telemetry link radio | +500mW, 433MHz variant, pair of transmitter + receiver** | +63 | +1 | +63 | +https://holybro.com/products/sik-telemetry-radio-v3?variant=42801817485501 | +
9 | +Tattu 5200mAh 4S | +Battery | +4S1P XT60 plug 35C | +63 | +1 | +63 | +https://genstattu.com/tattu-5200mah-14-8v-35c-4s1p-lipo-battery-pack-with-xt60-plug.html | +
+ | + | + | + | + | Grand Total | +624 | ++ |
Notes:
+*It can be used with Radiomaster Multiprotocol (4 in 1) or CC2500 based Radio Controller like FrSky Taranis X9D or similar
+**Used for connecting to ground control station, 915MHz variant also available
Useful tool for this page: +https://tabletomarkdown.com/convert-spreadsheet-to-markdown/
+ + +This repository/website is a collection of resources for aerial robotics. It is intended to be a comprehensive list of recourses for anyone interested in aerial robotics. The resources are divided into categories, such as autonomy stacks, autopilot suites, simulation, message standards, safety and management systems, tutorials and education, hardware, components, and development kits, aerial vehicle types, and middleware and drivers.
+Contributions are welcomed
+This project is under active development and you can contribute to it, by submiting a PR with you changes or posting an issue to the repository in Github.
+This landscape is a community project, and we encourage readers to +contribute to the landscape. The best way to contribute is to join our +bi-weekly meetings, and/or add to the lists.
+The main repository for the Community Work Group
+The Aerial Robotics group meets bi-weekly on Wednesday's at 16:00 UTC. +Meetings will be announced on the ROS Discourse Aerial Robotics forum category at least a week in advance, and recordings and meeting notes will be made available after each meeting.
+Contributions to the landscape are highly encouraged, from simple fixes +to spelling and grammer all the way to adding new sections to the +landscape.
+Simple changes to existing pages can be done by clicking the "Edit on +Github" link that appears at the top of every page.
+ +To edit an existing page: +1. Open the page. +2. Click the Edit on Github link on top of the page. +3. Make the changes in the online editor. +4. Below the Github page editor you'll be prompted to create a separate branch and then guided to submit a pull request.
+Once you submit the team will review your change request and either +provide feedback on how to improve or just merge it, resulting in the +website getting updated.
+More substantial changes, including adding new pages or adding/modifying images, aren't as easy to make (or properly test) on Github. For these kinds of changes we suggest using the same approach as for code:
+git clone git@github.com:ROS-Aerial/aerial_robotic_landscape.git
Within the ROS ecoysystem, there is currently a ROS enhancement proposal (REP) available to give guidance to message standards for UAVS. This can be found here:
+REP 147 A Standard interface for Aerial Vehicles
+MAVLink, an acronym for Micro Air Vehicle Link, is a communication system mainly used for the exchange of information between unmanned aerial vehicles and ground control stations. +This protocol, which was launched in 2009, is structured as a header-only message marshaling library. +MAVLink is versatile, supporting a broad range of messages and capable of being sent over virtually any type of serial connection, including Wi-Fi and radio technologies. +In terms of messages, they are defined at compile time in XML files, which are processed to create libraries for sending and receiving messages. +If new messages are added or existing ones are modified, the XML definitions need to be updated and the application recompiled.
+https://mavlink.io/en/
+MAVlink is used in 2 autopilot suites. Eventhough the same message type are being shared in both the suites, the accomendating behavior might differ:
+ + + +The aim for this page is to provide a collection of ROS packages/related libraries which are very useful for aerial ROS projects either to serve as a reference or directly use as a part of a custom software stack. This list aims to address the gap between the flight controller firmware and purely autonomy related packages.
+Enabling low overhead publish/subscribe on microcontrollers:
+ROS packages built atop SDKs from drone vendors to interface to their closed-source flight controller firmwares. Several of these may be for much older ROS1 distros but can have utility in terms of serving as references.
+ + + +Quadcopter and other Aerial vehicles come in all forms and sizes. +Safety systems are important for all, but the bigger an aerial vehicle becomes, the more important it becomes that the right fail-safes and emergency systems are in place! +This pages gives an overview of those safety systems that have been implemented so far.
+Currently specifically for aerial vehicles, the safety implementation is depended on the ROS autonomy stack used.
+The ROS-0147 has a suggestion for flightmodes for a statemachine that can simplify the understanding of it. It is also expecting that ROS will be run offboard on an external computer, and that it should be in control of the safety state machine. This should probably be discussed if it would be a good idea for ROS to be in control of this or the autopilot suites themselves.
+Adapted from the following blogpost: https://www.bitcraze.io/2023/04/safety-and-the-brushless/
+These are current Safety managements systems existing in Paparazzi UAV, Betaflight, ArduPilot and PX4. +The Crazyflie ecosystem also have some measures but are currently overhauling their safety framework now in the form of a supervisor.
+Before a vehicle can fly, certain conditions must be met. These includ:
+Preflight checks documentation:
+After passing pre-flight checks and arming the UAV, the takeoff command is given. However, UAV flights have inherent risks, particularly during takeoff. To mitigate these risks, numerous safety features, known as failsafes, are implemented during the flight phase. These failsafes are categorized as triggers and behaviors, allowing developers to specify the UAV's response to different failures, such as initiating a safe landing in the event of GPS loss.
+Thus, there are triggers that can enable the autopilot’s failsafe mechanics:
+Also, sometimes the support of an external Automatic Trigger system is required, which is a box that monitors the conditions where the UAV should take action in case there is no GPS, other aerial vehicles are nearby, or the UAV is crossing a geofence determined by outdoor flight restrictions. Note that all of these triggers usually have a couple of conditions attached, such as the level of the ‘low battery’ or the number of seconds of ‘GPS loss’ deemed acceptable.
+During UAV flights, safety features can be customized per trigger, deviating from the default actions set by regulations. Disarming the vehicle completely increases the risk of crashing and causing harm. Allowing the drone to autonomously complete the mission without intervention poses the risk of losing the vehicle or trespassing restricted areas. Modifying default behaviors should be undertaken by knowledgeable individuals with careful consideration.
+These behaviors can include the following:
+Fail-safe documentation
+Fail-safes ensure safe flight, but emergencies like crashes, flips, or hardware failures can still occur. In such cases, the standard default action is to disarm the vehicle to prevent unintended motor activation. Backup systems connected to ESCs may take over if the autopilot becomes unresponsive. The pilot plays a vital role in safety, with the remote control featuring a dedicated button or switch for different modes, enabling actions like landing or disarming. It's recommended to have a net or towel to stop spinning motors and to promptly disconnect the battery. Being prepared for potential LiPo battery hazards is essential, with sand or fire retardant on hand. While autopilots provide guidance, conducting thorough research on handling emergencies, spinning parts, and LiPo battery fires is crucial.
+Here a list of that: +* Remote control should have a dedicated button/switch for different modes, landing, or disarming. +* Dealing with spinning motors Use a net or towel to stop them and promptly disconnect the battery. +* To prepare for LiPo battery hazards, Have sand or fire retardant available.
+ + +' + escapeHtml(summary) +'
' + noResultsText + '
'); + } +} + +function doSearch () { + var query = document.getElementById('mkdocs-search-query').value; + if (query.length > min_search_length) { + if (!window.Worker) { + displayResults(search(query)); + } else { + searchWorker.postMessage({query: query}); + } + } else { + // Clear results for short queries + displayResults([]); + } +} + +function initSearch () { + var search_input = document.getElementById('mkdocs-search-query'); + if (search_input) { + search_input.addEventListener("keyup", doSearch); + } + var term = getSearchTermFromLocation(); + if (term) { + search_input.value = term; + doSearch(); + } +} + +function onWorkerMessage (e) { + if (e.data.allowSearch) { + initSearch(); + } else if (e.data.results) { + var results = e.data.results; + displayResults(results); + } else if (e.data.config) { + min_search_length = e.data.config.min_search_length-1; + } +} + +if (!window.Worker) { + console.log('Web Worker API not supported'); + // load index in main thread + $.getScript(joinUrl(base_url, "search/worker.js")).done(function () { + console.log('Loaded worker'); + init(); + window.postMessage = function (msg) { + onWorkerMessage({data: msg}); + }; + }).fail(function (jqxhr, settings, exception) { + console.error('Could not load worker.js'); + }); +} else { + // Wrap search in a web worker + var searchWorker = new Worker(joinUrl(base_url, "search/worker.js")); + searchWorker.postMessage({init: true}); + searchWorker.onmessage = onWorkerMessage; +} diff --git a/search/search_index.json b/search/search_index.json new file mode 100644 index 0000000..f76f608 --- /dev/null +++ b/search/search_index.json @@ -0,0 +1 @@ +{"config":{"indexing":"full","lang":["en"],"min_search_length":3,"prebuild_index":false,"separator":"[\\s\\-]+"},"docs":[{"location":"","text":"Aerial Robotic Landscape This repository/website is a collection of resources for aerial robotics. It is intended to be a comprehensive list of recourses for anyone interested in aerial robotics. The resources are divided into categories, such as autonomy stacks, autopilot suites, simulation, message standards, safety and management systems, tutorials and education, hardware, components, and development kits, aerial vehicle types, and middleware and drivers. Contributions are welcomed This project is under active development and you can contribute to it, by submiting a PR with you changes or posting an issue to the repository in Github. Community This landscape is a community project, and we encourage readers to contribute to the landscape. The best way to contribute is to join our bi-weekly meetings, and/or add to the lists. The main repository for the Community Work Group Meetings The Aerial Robotics group meets bi-weekly on Wednesday's at 16:00 UTC. Meetings will be announced on the ROS Discourse Aerial Robotics forum category at least a week in advance, and recordings and meeting notes will be made available after each meeting. Team / Community Coordination Instant Messaging ROS Discord: under the #cwg-aerial Forums ROS Discourse Aerial Robotics Category Contributing Contributions to the landscape are highly encouraged, from simple fixes to spelling and grammer all the way to adding new sections to the landscape. Quick Changes in Github Simple changes to existing pages can be done by clicking the \"Edit on Github\" link that appears at the top of every page. To edit an existing page: 1. Open the page. 2. Click the Edit on Github link on top of the page. 3. Make the changes in the online editor. 4. Below the Github page editor you'll be prompted to create a separate branch and then guided to submit a pull request. Once you submit the team will review your change request and either provide feedback on how to improve or just merge it, resulting in the website getting updated. Changes using Git (New Pages and Images) More substantial changes, including adding new pages or adding/modifying images, aren't as easy to make (or properly test) on Github. For these kinds of changes we suggest using the same approach as for code: Use the git toolchain to get the documentation source code onto your local computer with git clone git@github.com:ROS-Aerial/aerial_robotic_landscape.git Modify the documentation as needed (add, change, delete). Test that it builds properly with mkdocs . Check out their documentation for building the website and trying the website locally. Create a branch for your changes and create a pull request (PR) to pull it back into the documentation.","title":"Aerial Robotic Landscape"},{"location":"#aerial-robotic-landscape","text":"This repository/website is a collection of resources for aerial robotics. It is intended to be a comprehensive list of recourses for anyone interested in aerial robotics. The resources are divided into categories, such as autonomy stacks, autopilot suites, simulation, message standards, safety and management systems, tutorials and education, hardware, components, and development kits, aerial vehicle types, and middleware and drivers. Contributions are welcomed This project is under active development and you can contribute to it, by submiting a PR with you changes or posting an issue to the repository in Github.","title":"Aerial Robotic Landscape"},{"location":"#community","text":"This landscape is a community project, and we encourage readers to contribute to the landscape. The best way to contribute is to join our bi-weekly meetings, and/or add to the lists. The main repository for the Community Work Group","title":"Community"},{"location":"#meetings","text":"The Aerial Robotics group meets bi-weekly on Wednesday's at 16:00 UTC. Meetings will be announced on the ROS Discourse Aerial Robotics forum category at least a week in advance, and recordings and meeting notes will be made available after each meeting.","title":"Meetings"},{"location":"#team-community-coordination","text":"Instant Messaging ROS Discord: under the #cwg-aerial Forums ROS Discourse Aerial Robotics Category","title":"Team / Community Coordination"},{"location":"#contributing","text":"Contributions to the landscape are highly encouraged, from simple fixes to spelling and grammer all the way to adding new sections to the landscape.","title":"Contributing"},{"location":"#quick-changes-in-github","text":"Simple changes to existing pages can be done by clicking the \"Edit on Github\" link that appears at the top of every page. To edit an existing page: 1. Open the page. 2. Click the Edit on Github link on top of the page. 3. Make the changes in the online editor. 4. Below the Github page editor you'll be prompted to create a separate branch and then guided to submit a pull request. Once you submit the team will review your change request and either provide feedback on how to improve or just merge it, resulting in the website getting updated.","title":"Quick Changes in Github"},{"location":"#changes-using-git-new-pages-and-images","text":"More substantial changes, including adding new pages or adding/modifying images, aren't as easy to make (or properly test) on Github. For these kinds of changes we suggest using the same approach as for code: Use the git toolchain to get the documentation source code onto your local computer with git clone git@github.com:ROS-Aerial/aerial_robotic_landscape.git Modify the documentation as needed (add, change, delete). Test that it builds properly with mkdocs . Check out their documentation for building the website and trying the website locally. Create a branch for your changes and create a pull request (PR) to pull it back into the documentation.","title":"Changes using Git (New Pages and Images)"},{"location":"aerial_autonomy_stacks/","text":"Aerial Autonomy Stacks Based on this discussion in Discourse and our startup meeting , we can define an aerial autonomy stack as follows: An aerial autonomy robotics stack is a collection of building blocks that enable the development of autonomous aerial vehicles, by providing a modular and scalable architecture for sensing, perception, planning, and control tasks. It allows unmanned aerial vehicles to perform complex missions without human intervention, while accommodating different hardware configurations and simulation environments. Comparison From the paper Fernandez-Cortizas, Miguel, et al. \"Aerostack2: A Software Framework for Developing Multi-robot Aerial Systems.\" arXiv preprint arXiv:2303.18237 (2023). the following autonomy stack table was extracted and adapted. Flight stack OS/OC Modular Tested in Middleware last update MF RO MA MP PO Aerostack \u2713 \u2713 S,RIL,ROL ROS 10/2021 \u2717 \u2713 \u2713 \u2713 \u2717 Aerostack2 \u2713 \u2713 S,RIL,ROL ROS 2 03/2023 \u2713 \u2713 \u2713 \u2713 \u2713 AerialCore \u2713 \u2713 S,RIL,ROL ROS 03/2023 \u2713 \u2713 \u2713 \u2717 \u2713 Agilicious \u2713 \u2713 S,RIL ROS 03/2023 \u2717 \u2713 \u2717 \u2717 \u2717 KumarRobotics \u2713 \u2717 S,RIL,ROL ROS 12/2022 \u2717 \u2713 \u2717 \u2713 \u2717 CrazyChoir \u2713 \u2717 S,RIL ROS 2 02/2023 \u2717 \u2713 \u2713 \u2717 \u2717 UAL \u2713 \u2717 S,RIL,ROL ROS 12/2022 \u2713 \u2717 \u2717 \u2713 \u2717 XTDrone \u2713 \u2713 S ROS 03/2023 \u2717 \u2713 \u2717 \u2717 \u2717 RotorS \u2713 \u2713 S ROS 07/2021 \u2717 \u2713 \u2717 \u2717 \u2717 GAAS \u2713 \u2713 S ROS 10/2021 \u2717 \u2717 \u2717 \u2717 \u2717 MRS AUV System \u2713 \u2713 S,RIL,ROL ROS 09/2023 \u2713 \u2713 \u2713 \u2713 \u2717 Crazyswarm \u2713 \u2717 S,RIL ROS 12/2022 \u2717 \u2713 \u2713 \u2717 \u2717 Crazyswarm2 \u2713 \u2713 S,RIL ROS 2 09/2023 \u2717 \u2713 \u2713 \u2717 \u2713 Abbrivations * OS/OC: Open source or Open code * S: Experiments in simulation * RIL: Experiments in the lab * ROL: Experiments outside the lab * MF: Multi-frame * RO: Rate output * MA: Multi agent * MP: Multi platform * PO: Plugin oriented VIO packages Visual Inertial Odometry packages is an very important strategy of positioning within GPS deprived environments. Since UAVs can not use wheel odometry and heavily relient on cameras, this is one of the main drivers for autonomous exploration with these vehicles. Here is a list of VIO packages that people can use if they have a depth camera on their platform. OpenVins (ROS1/ROS2): VINS-Fusion stand alone SLAMcore stand alone SDK ORB-SLAM3 ROS2 Visual Odometry Datasets Kaggle Zurich Urban Micro Aerial Vehicle Kaggle Underwater forward-looking VI dataset The Air Lab Datasets VICON ROS2 bag file Google drive The UZH FPV Dataset Working list autonomy stacks This is just a list of autonomy stacks with links, such that later we can add them to the overview. Working list: Aerostack2 Aerostack(1) KumarRobotics Autonomy Stack Agilicious Crazyswarm2 Crazyswarm(1) MRS UAV System Hector quadrotor RotorS RISE paper MRS AUV System Clover /HKUST-Aerial-Robotics Partial autonomy packages A list of packages which don't comprise a full stack but do offer value on top of basic flight controller firmware. MAVROS Controllers Indoor navigation packages Given the above Aerial Autonomy Stacks , the list below outlines specific implementations of indoor navigation software packages in ROS, running on aerial vehicle platforms. The list, though not exhaustive, provides a good overview of available off-the-shelf non-commercial software. Package name OS/OC Sensors required Middleware Simulator Platform/controller Last updated Ardupilot ROS \u2713 LiDAR ROS 2 Gazebo Iris coptor,Ardupilot 02/2024 as2_behaviour_tree \u2713 Unknown ROS 2 Gazebo Crazyflie,DJI,Tello 02/2024 Teach-Repeat-Replan \u2713 Stereo camera ROS 1 MockaFly DJI N3 11/2020 rtabmap \u2713 Stereo camera ROS 1 Gazebo PX4 05/2023 ORB_SLAM_3 \u2713 Mono/stereo camera ROS 1 N/A Bebop 2 06/2023 relative_nav \u2717 Stereo camera ROS 1 N/A Rotorcraft 04/2017 zephyr \u2713 LiDAR ROS 1 RotorS/Gazebo AscTec Firefly 11/2018 tum_ardrone \u2713 Mono camera ROS 1 N/A AR.Drone 05/2014 kr_autonomous_flight \u2713 Stereo camera/LiDAR/IMU ROS 1 Gazebo Pixhawk 08/2023 px4_sim_ros2 \u2713 Stereo camera ROS 2 Gazebo PX4 04/2024","title":"Aerial Autonomy Stacks"},{"location":"aerial_autonomy_stacks/#aerial-autonomy-stacks","text":"Based on this discussion in Discourse and our startup meeting , we can define an aerial autonomy stack as follows: An aerial autonomy robotics stack is a collection of building blocks that enable the development of autonomous aerial vehicles, by providing a modular and scalable architecture for sensing, perception, planning, and control tasks. It allows unmanned aerial vehicles to perform complex missions without human intervention, while accommodating different hardware configurations and simulation environments.","title":"Aerial Autonomy Stacks"},{"location":"aerial_autonomy_stacks/#comparison","text":"From the paper Fernandez-Cortizas, Miguel, et al. \"Aerostack2: A Software Framework for Developing Multi-robot Aerial Systems.\" arXiv preprint arXiv:2303.18237 (2023). the following autonomy stack table was extracted and adapted. Flight stack OS/OC Modular Tested in Middleware last update MF RO MA MP PO Aerostack \u2713 \u2713 S,RIL,ROL ROS 10/2021 \u2717 \u2713 \u2713 \u2713 \u2717 Aerostack2 \u2713 \u2713 S,RIL,ROL ROS 2 03/2023 \u2713 \u2713 \u2713 \u2713 \u2713 AerialCore \u2713 \u2713 S,RIL,ROL ROS 03/2023 \u2713 \u2713 \u2713 \u2717 \u2713 Agilicious \u2713 \u2713 S,RIL ROS 03/2023 \u2717 \u2713 \u2717 \u2717 \u2717 KumarRobotics \u2713 \u2717 S,RIL,ROL ROS 12/2022 \u2717 \u2713 \u2717 \u2713 \u2717 CrazyChoir \u2713 \u2717 S,RIL ROS 2 02/2023 \u2717 \u2713 \u2713 \u2717 \u2717 UAL \u2713 \u2717 S,RIL,ROL ROS 12/2022 \u2713 \u2717 \u2717 \u2713 \u2717 XTDrone \u2713 \u2713 S ROS 03/2023 \u2717 \u2713 \u2717 \u2717 \u2717 RotorS \u2713 \u2713 S ROS 07/2021 \u2717 \u2713 \u2717 \u2717 \u2717 GAAS \u2713 \u2713 S ROS 10/2021 \u2717 \u2717 \u2717 \u2717 \u2717 MRS AUV System \u2713 \u2713 S,RIL,ROL ROS 09/2023 \u2713 \u2713 \u2713 \u2713 \u2717 Crazyswarm \u2713 \u2717 S,RIL ROS 12/2022 \u2717 \u2713 \u2713 \u2717 \u2717 Crazyswarm2 \u2713 \u2713 S,RIL ROS 2 09/2023 \u2717 \u2713 \u2713 \u2717 \u2713 Abbrivations * OS/OC: Open source or Open code * S: Experiments in simulation * RIL: Experiments in the lab * ROL: Experiments outside the lab * MF: Multi-frame * RO: Rate output * MA: Multi agent * MP: Multi platform * PO: Plugin oriented","title":"Comparison"},{"location":"aerial_autonomy_stacks/#vio-packages","text":"Visual Inertial Odometry packages is an very important strategy of positioning within GPS deprived environments. Since UAVs can not use wheel odometry and heavily relient on cameras, this is one of the main drivers for autonomous exploration with these vehicles. Here is a list of VIO packages that people can use if they have a depth camera on their platform. OpenVins (ROS1/ROS2): VINS-Fusion stand alone SLAMcore stand alone SDK ORB-SLAM3 ROS2","title":"VIO packages"},{"location":"aerial_autonomy_stacks/#visual-odometry-datasets","text":"Kaggle Zurich Urban Micro Aerial Vehicle Kaggle Underwater forward-looking VI dataset The Air Lab Datasets VICON ROS2 bag file Google drive The UZH FPV Dataset","title":"Visual Odometry Datasets"},{"location":"aerial_autonomy_stacks/#working-list-autonomy-stacks","text":"This is just a list of autonomy stacks with links, such that later we can add them to the overview. Working list: Aerostack2 Aerostack(1) KumarRobotics Autonomy Stack Agilicious Crazyswarm2 Crazyswarm(1) MRS UAV System Hector quadrotor RotorS RISE paper MRS AUV System Clover /HKUST-Aerial-Robotics","title":"Working list autonomy stacks"},{"location":"aerial_autonomy_stacks/#partial-autonomy-packages","text":"A list of packages which don't comprise a full stack but do offer value on top of basic flight controller firmware. MAVROS Controllers","title":"Partial autonomy packages"},{"location":"aerial_autonomy_stacks/#indoor-navigation-packages","text":"Given the above Aerial Autonomy Stacks , the list below outlines specific implementations of indoor navigation software packages in ROS, running on aerial vehicle platforms. The list, though not exhaustive, provides a good overview of available off-the-shelf non-commercial software. Package name OS/OC Sensors required Middleware Simulator Platform/controller Last updated Ardupilot ROS \u2713 LiDAR ROS 2 Gazebo Iris coptor,Ardupilot 02/2024 as2_behaviour_tree \u2713 Unknown ROS 2 Gazebo Crazyflie,DJI,Tello 02/2024 Teach-Repeat-Replan \u2713 Stereo camera ROS 1 MockaFly DJI N3 11/2020 rtabmap \u2713 Stereo camera ROS 1 Gazebo PX4 05/2023 ORB_SLAM_3 \u2713 Mono/stereo camera ROS 1 N/A Bebop 2 06/2023 relative_nav \u2717 Stereo camera ROS 1 N/A Rotorcraft 04/2017 zephyr \u2713 LiDAR ROS 1 RotorS/Gazebo AscTec Firefly 11/2018 tum_ardrone \u2713 Mono camera ROS 1 N/A AR.Drone 05/2014 kr_autonomous_flight \u2713 Stereo camera/LiDAR/IMU ROS 1 Gazebo Pixhawk 08/2023 px4_sim_ros2 \u2713 Stereo camera ROS 2 Gazebo PX4 04/2024","title":"Indoor navigation packages"},{"location":"aerial_vehicles/","text":"Aerial Vehicle Types and Categories Usually, people tend to think about quadcopters when talking about aerial robotics, but there is actually a much larger variety of vehicle types available! Here's an attempt to list all of them if we can. Copters Copters are aerial vehicles that use motors and propellers for their lift and maneuverability in 3D space. These usually are categorized into the following subcategories: Quadcopters: The most common aerial vehicle used. It is driven by (as the name already indicates) 4 propellers and 4 motors. Helicopters: Like manned helicopters, unmanned helicopters are driven by one main rotor on top and one smaller one on the side for stability and maneuverability. Hexacopters/Octocopters: Copters with 6 or 8 rotors/motor combinations, respectively. Tilt-Rotor Copters: Copters that have motor and rotor combos that can change orientation. Monocopters: Monocopters are copters that are only driven by a single rotor and motor combo. Fixed Wing Fixed-wing aerial vehicles use fixed wings for takeoff lift and control. These are the subcategories: Regular Fixed Wings: Like regular airplanes, fixed-wing UAVs have 2 wings with a form of propulsion. Hybrid / VTOL: These vehicles can take off like a quadcopter vertically but can transition and act like a fixed-wing vehicle for the remainder of the flight. Gliding UAVs: These are fixed-wing UAVs without any propulsion and are therefore reliant on wind and thermal currents. Flapping Wing Flapping-wing aerial vehicles generate both lift and thrust by their flapping wings. There are two main subcategories: Ornithopters: These are the traditional bird-like flapping-wing UAVs. The flapping wings generate lift and thrust and an airplane-like tail with traditional control surfaces is used for stbility and flight control. Some minimal forward velocity needs to be maintained such the wings produce sufficient lift. Only some smaller vehicles demonstrate limited VTOL and hovering capability. These vehicles can be passively stabilized by the tail surfaces and do not require active stabilization, similar to fixed-wing UAVs. Tail-less flapping-wing UAVs: These vehicles fly like insects and hummingbirds - they can hover, take-off and land vertically, and fly in any direction (forward & backward, sideways, up & down). Lift/thrust is generated by the flapping wings, whose geometry and/or motion is adjustable for flight control. Like multicopters, these vehicles require active stabilization, typically by using an onboard IMU. Blimps Blimps or airships can also be used as aerial vehicles as well. These vehicles stay buoyant by using a balloon with lighter-than-air gas. Maneuverability is either done with flapping wings or rotors. List to support vehicles per autopilot suite Each autopilot suite have their a wide range of supported vehicles, to which this itemized list is referenced to. Note that these lists also include non-aerial vehicles as well. Ardupilot supported vehicle types Paparazzi PX4 Crazyflie","title":"Aerial Vehicle Types and Categories"},{"location":"aerial_vehicles/#aerial-vehicle-types-and-categories","text":"Usually, people tend to think about quadcopters when talking about aerial robotics, but there is actually a much larger variety of vehicle types available! Here's an attempt to list all of them if we can.","title":"Aerial Vehicle Types and Categories"},{"location":"aerial_vehicles/#copters","text":"Copters are aerial vehicles that use motors and propellers for their lift and maneuverability in 3D space. These usually are categorized into the following subcategories: Quadcopters: The most common aerial vehicle used. It is driven by (as the name already indicates) 4 propellers and 4 motors. Helicopters: Like manned helicopters, unmanned helicopters are driven by one main rotor on top and one smaller one on the side for stability and maneuverability. Hexacopters/Octocopters: Copters with 6 or 8 rotors/motor combinations, respectively. Tilt-Rotor Copters: Copters that have motor and rotor combos that can change orientation. Monocopters: Monocopters are copters that are only driven by a single rotor and motor combo.","title":"Copters"},{"location":"aerial_vehicles/#fixed-wing","text":"Fixed-wing aerial vehicles use fixed wings for takeoff lift and control. These are the subcategories: Regular Fixed Wings: Like regular airplanes, fixed-wing UAVs have 2 wings with a form of propulsion. Hybrid / VTOL: These vehicles can take off like a quadcopter vertically but can transition and act like a fixed-wing vehicle for the remainder of the flight. Gliding UAVs: These are fixed-wing UAVs without any propulsion and are therefore reliant on wind and thermal currents.","title":"Fixed Wing"},{"location":"aerial_vehicles/#flapping-wing","text":"Flapping-wing aerial vehicles generate both lift and thrust by their flapping wings. There are two main subcategories: Ornithopters: These are the traditional bird-like flapping-wing UAVs. The flapping wings generate lift and thrust and an airplane-like tail with traditional control surfaces is used for stbility and flight control. Some minimal forward velocity needs to be maintained such the wings produce sufficient lift. Only some smaller vehicles demonstrate limited VTOL and hovering capability. These vehicles can be passively stabilized by the tail surfaces and do not require active stabilization, similar to fixed-wing UAVs. Tail-less flapping-wing UAVs: These vehicles fly like insects and hummingbirds - they can hover, take-off and land vertically, and fly in any direction (forward & backward, sideways, up & down). Lift/thrust is generated by the flapping wings, whose geometry and/or motion is adjustable for flight control. Like multicopters, these vehicles require active stabilization, typically by using an onboard IMU.","title":"Flapping Wing"},{"location":"aerial_vehicles/#blimps","text":"Blimps or airships can also be used as aerial vehicles as well. These vehicles stay buoyant by using a balloon with lighter-than-air gas. Maneuverability is either done with flapping wings or rotors.","title":"Blimps"},{"location":"aerial_vehicles/#list-to-support-vehicles-per-autopilot-suite","text":"Each autopilot suite have their a wide range of supported vehicles, to which this itemized list is referenced to. Note that these lists also include non-aerial vehicles as well. Ardupilot supported vehicle types Paparazzi PX4 Crazyflie","title":"List to support vehicles per autopilot suite"},{"location":"autopilots_suites/","text":"Autopilot Suites There are several autopilot suites available for control-boards for aerial vehicles. This page mostly have an overview of all of those including some comparison factors in them as well. Autopilot suite startup year latest version OS licence ROS support supported vehicles Ardupilot ( GitHub ) 2009 4.5.2 (05/24) GPL 3.0 yes Copters, Fixed wings, VTOL Betaflight ( GitHub ) 2015 4.5.0 (04/24) GPL 3.0 no Copters crazyflie-firmware ( GitHub ) 2011 2024.2 GPL 3.0 yes* Quadcopters, Flapping wings DJI autopilot ( GitHub ) 2006 2023.9 closed yes Copters, VTOLS Paparazzi ( GitHub ) 2003 6.3.0 (12/23) GPL 2.0 no Copters, Fixed wings, VTOL PX4 ( GitHub ) 2009 1.14.0 (10/23) BSD 3-Clause yes Copters, Fixed wings, VTOL ROSflight ( GitHub ) 2019 2.2.0 beta (09/23) BSD 3-Clause yes Copters, fixed wings *community provided support","title":"Autopilot Suites"},{"location":"autopilots_suites/#autopilot-suites","text":"There are several autopilot suites available for control-boards for aerial vehicles. This page mostly have an overview of all of those including some comparison factors in them as well. Autopilot suite startup year latest version OS licence ROS support supported vehicles Ardupilot ( GitHub ) 2009 4.5.2 (05/24) GPL 3.0 yes Copters, Fixed wings, VTOL Betaflight ( GitHub ) 2015 4.5.0 (04/24) GPL 3.0 no Copters crazyflie-firmware ( GitHub ) 2011 2024.2 GPL 3.0 yes* Quadcopters, Flapping wings DJI autopilot ( GitHub ) 2006 2023.9 closed yes Copters, VTOLS Paparazzi ( GitHub ) 2003 6.3.0 (12/23) GPL 2.0 no Copters, Fixed wings, VTOL PX4 ( GitHub ) 2009 1.14.0 (10/23) BSD 3-Clause yes Copters, Fixed wings, VTOL ROSflight ( GitHub ) 2019 2.2.0 beta (09/23) BSD 3-Clause yes Copters, fixed wings *community provided support","title":"Autopilot Suites"},{"location":"education_and_tutorial/","text":"Education and tutorials This page will contain a list of education courses or tutorials for aerial robotics. This is a partly compilation of this ROS discourse thread and the May meeting about tutorials and education and some googling :) This also includes input from a Linkedin post for a call of suggestions. This has been an adaption from the following Bitcraze Blogpost , and the overview presentation done for the ROS-aerial CWG meetings Course explanation This section explains some of the recourses in more detail. Books There is this important resource which is the book titled \u2018Small Unmanned Aircraft: Theory and Practice.\u2019 This book has been written by Randy Beard and Tim McLain of Brigham Young University, and it covers everything from the absolute basics of coordinate frames and quadrotor dynamics to path planning and cameras. It is a must-read for anybody starting in UAVs and Aerial robotics. The physical book can be found here: http://press.princeton.edu/titles/9632.html The available PDFs can be accessed on GitHub: https://github.com/randybeard/uavbook Online Courses on Aerial Robotics This section shows online courses for aerial robotics with online instructor. Coursera offers the \u2018Robotics: Aerial Robotics\u2019 course as part of the Robotics specialization. Taught by Prof. Vijay Kumar from Penn University, this 4-week course covers the mechanics and control of aerial vehicles using Matlab. It starts from 1 dimension and gradually progresses to the 3rd dimension in simulation. The course is part of a paid educational program, but you can audit the lessons for free. Link: https://www.coursera.org/learn/robotics-flight Udacity has been offering a course on Aerial Vehicles for quite some time for the Flying car nano degree . The lessons are taught by top names in the industry and cover key aspects of Aerial Robotics, such as motion planning, controls, and estimation, with lab assignments involving a real drone. The course duration is 4 months, and access is available for a fee. Link: https://www.udacity.com/course/flying-car-nanodegree\u2013nd787 edX offers the 'ETHx: Autonomous Mobile Robots' course. Taught by Prof. Roland Siegwart, Dr. Davide Scaramuzza, Prof. Marco Hutter, Prof. Margarita Chli, Prof. Martin Rufli and Prof. Nicholas Lawrance from ETH Zurich, this 15-week course focuses on the principles of autonomous navigation and control of mobile robots. It covers topics such as perception, localization, planning, and control, which are essential for enabling robots to operate autonomously in dynamic environments. You can audit the course material for free with limited access. Link: https://www.edx.org/learn/autonomous-robotics/eth-zurich-autonomous-mobile-robots?utm_campaign=social-sharing-course-page&utm_medium=social&utm_source=email Additionally, there\u2019s the course \u2018Applied Control System 3: UAV Drone (3D Dynamics & Control)\u2019 which is part of a series by Mark Misin. This course delves deep into the dynamics, control, and modeling of quadrotors. Link: https://www.udemy.com/course/applied-control-systems-for-engineers-2-uav-drone-control/ University courses on Aerial Robotics with open resources This section showes university courses that have released recordings of lectures, slides and/or assignments. For instructions participants would need to follow the actual course at that one university. The University of Maryland offers a course on Autonomous Aerial Robotics , making all videos, slides, and assignments available. Taught by Nitin J. Sanket and Chahat Deep Singh, the course covers everything from basic control and dynamics to full autonomy. It\u2019s a comprehensive resource for aerial robotics. The course utilizes the Parrot Bebop 2.0 , and while a Mocap system is required, you may explore the possibility of adapting the course to a different platform. ROS is also part of this course Link: http://prg.cs.umd.edu/enae788m \u2018Visual Navigation For Autonomous Vehicles\u2019 is a course available on MIT Open Courseware, taught by Prof. Luca Carlone. As the name implies, the course primarily focuses on autonomous navigation for any autonomous vehicle. It includes exercises where students implement vision algorithms on both ground robots and drones. Additionally, the course covers working with ROS and applying the knowledge to a simulated drone in Unity. The students also get to learn how to work with ROS Link: https://ocw.mit.edu/courses/16-485-visual-navigation-for-autonomous-vehicles-vnav-fall-2020/ The \u2018Bio-inspired Robotics\u2019 course at the University of Washington, led by Prof. Sawyer Fuller, explores the realm of drawing inspiration from nature rather than reinventing the wheel. It covers various robots inspired by creatures capable of swimming, walking, hopping, and of course, flying. Lab assignments in this course involve working with a Crazyflie drone. Link: https://faculty.washington.edu/minster/bio_inspired_robotics/ Brown University offers a course called \u2018Introduction to Robotics\u2019 taught by Prof. Stefanie Tellix. While the introduction covers generic robotics, the focus of the full course is on building and programming the Duckiedrone . The course dives straight into autonomy and also teaches students how to work with ROS . Link: https://cs.brown.edu/courses/cs1951r/ Princeton University have also decided to release their \u2018Intro to Robotics\u2019 lectures and materials for the public. It covers all from control and estimation, computer vision and planning. Also it offers lab assignments with the Crazyflie . Link: https://irom-lab.princeton.edu/intro-to-robotics/ Youtube Youtube also has quite some tutorials available so this section highlights a few. Drone Programming with Python : This popular tutorial/course teaches viewers how to program a real drone using Python with the DJI Tello . It offers a great opportunity for anyone looking for a short and enjoyable project to undertake, especially on a rainy day, while still working with a real platform. Link: https://youtu.be/LmEcyQnfpDA Intelligent Quads YouTube Channel : This channel is entirely dedicated to creating autonomous UAVs, covering topics from Ardupilot to MAVlink to ROS and Gazebo. It appears to be a valuable resource for beginners in the field of autonomous UAVs. This also includes ROS as part of the lessons as well. Link: https://www.youtube.com/@IntelligentQuads Code Examples Here are some code examples that can be used as reference for experiments. Mambo ROS Examples: This is a collection of experiments targeted Parrot Mambo drones, there are experiments with one or multiple vehicles at the same time. It runs over ROS over BLE, and some test are adapted to make use of a Vicon MoCap system. From a control theory's perspective, it showcases an optional robust control strategy, using an H-Infinity controller with perturbation estimation and a identified dynamic model of a Parrot Mambo drone. Link: https://github.com/TOTON95/Mambo_ROS_Examples Some special mentions So here there are some courses that either doesn't fit in the above categories or are deprecated. University of Twente UAV Centre: The University of Twente has created a portal with a variety of UAV-related courses. You can find a wealth of information and educational materials on their website. Link: https://www.itc.nl/facilities/centres-of-expertise/uav-centre/ Self-Driving Car Specialization: If you are interested in learning more about SLAM (Simultaneous Localization and Mapping) and sensors, this specialization is tailored for self-driving cars but the theory can be useful for drones as well. Link: https://www.coursera.org/specializations/self-driving-cars Autonomous Navigation for Flying Robots: This older course is still highly relevant for anyone interested in autonomous navigation for flying robots. It offers valuable insights and knowledge. Link: https://www.edx.org/course/autonomous-navigation-for-flying-robots Drone Dojo: For those looking to build their own drones, Drone Dojo provides useful instructions and courses to get started on DIY drone projects. Link: https://dojofordrones.com/ Bachelor Majors in UAV Engineering: If you are fully committed to pursuing a career in aerial robotics, both Embry-Riddle Aeronautical University and the University of North Dakota offer full bachelor\u2019s majors in becoming a UAV engineer. Embry-Riddle Aeronautical University: https://erau.edu/degrees/bachelor/unmanned-aircraft-systems University of North Dakota: https://und.edu/programs/unmanned-aircraft-system-operations-bs-aero/ Working list This list contains some resources that we haven't included in the overview. Remove the item once it has been included PX4 getting started page Learning ArduPilot Aerial robotics 101 medium article Aerial robotics with ROS (work in progress) Bitcraze crazyflie tutorial page Simnet + Ardupilot academy Autonomy course Worcester Polytechnic Institute List of robotic aerial resources Credit Lots of thanks for anybody contributing to this linkedin post . This was extremely helpful!","title":"Education and tutorials"},{"location":"education_and_tutorial/#education-and-tutorials","text":"This page will contain a list of education courses or tutorials for aerial robotics. This is a partly compilation of this ROS discourse thread and the May meeting about tutorials and education and some googling :) This also includes input from a Linkedin post for a call of suggestions. This has been an adaption from the following Bitcraze Blogpost , and the overview presentation done for the ROS-aerial CWG meetings","title":"Education and tutorials"},{"location":"education_and_tutorial/#course-explanation","text":"This section explains some of the recourses in more detail.","title":"Course explanation"},{"location":"education_and_tutorial/#books","text":"There is this important resource which is the book titled \u2018Small Unmanned Aircraft: Theory and Practice.\u2019 This book has been written by Randy Beard and Tim McLain of Brigham Young University, and it covers everything from the absolute basics of coordinate frames and quadrotor dynamics to path planning and cameras. It is a must-read for anybody starting in UAVs and Aerial robotics. The physical book can be found here: http://press.princeton.edu/titles/9632.html The available PDFs can be accessed on GitHub: https://github.com/randybeard/uavbook","title":"Books"},{"location":"education_and_tutorial/#online-courses-on-aerial-robotics","text":"This section shows online courses for aerial robotics with online instructor. Coursera offers the \u2018Robotics: Aerial Robotics\u2019 course as part of the Robotics specialization. Taught by Prof. Vijay Kumar from Penn University, this 4-week course covers the mechanics and control of aerial vehicles using Matlab. It starts from 1 dimension and gradually progresses to the 3rd dimension in simulation. The course is part of a paid educational program, but you can audit the lessons for free. Link: https://www.coursera.org/learn/robotics-flight Udacity has been offering a course on Aerial Vehicles for quite some time for the Flying car nano degree . The lessons are taught by top names in the industry and cover key aspects of Aerial Robotics, such as motion planning, controls, and estimation, with lab assignments involving a real drone. The course duration is 4 months, and access is available for a fee. Link: https://www.udacity.com/course/flying-car-nanodegree\u2013nd787 edX offers the 'ETHx: Autonomous Mobile Robots' course. Taught by Prof. Roland Siegwart, Dr. Davide Scaramuzza, Prof. Marco Hutter, Prof. Margarita Chli, Prof. Martin Rufli and Prof. Nicholas Lawrance from ETH Zurich, this 15-week course focuses on the principles of autonomous navigation and control of mobile robots. It covers topics such as perception, localization, planning, and control, which are essential for enabling robots to operate autonomously in dynamic environments. You can audit the course material for free with limited access. Link: https://www.edx.org/learn/autonomous-robotics/eth-zurich-autonomous-mobile-robots?utm_campaign=social-sharing-course-page&utm_medium=social&utm_source=email Additionally, there\u2019s the course \u2018Applied Control System 3: UAV Drone (3D Dynamics & Control)\u2019 which is part of a series by Mark Misin. This course delves deep into the dynamics, control, and modeling of quadrotors. Link: https://www.udemy.com/course/applied-control-systems-for-engineers-2-uav-drone-control/","title":"Online Courses on Aerial Robotics"},{"location":"education_and_tutorial/#university-courses-on-aerial-robotics-with-open-resources","text":"This section showes university courses that have released recordings of lectures, slides and/or assignments. For instructions participants would need to follow the actual course at that one university. The University of Maryland offers a course on Autonomous Aerial Robotics , making all videos, slides, and assignments available. Taught by Nitin J. Sanket and Chahat Deep Singh, the course covers everything from basic control and dynamics to full autonomy. It\u2019s a comprehensive resource for aerial robotics. The course utilizes the Parrot Bebop 2.0 , and while a Mocap system is required, you may explore the possibility of adapting the course to a different platform. ROS is also part of this course Link: http://prg.cs.umd.edu/enae788m \u2018Visual Navigation For Autonomous Vehicles\u2019 is a course available on MIT Open Courseware, taught by Prof. Luca Carlone. As the name implies, the course primarily focuses on autonomous navigation for any autonomous vehicle. It includes exercises where students implement vision algorithms on both ground robots and drones. Additionally, the course covers working with ROS and applying the knowledge to a simulated drone in Unity. The students also get to learn how to work with ROS Link: https://ocw.mit.edu/courses/16-485-visual-navigation-for-autonomous-vehicles-vnav-fall-2020/ The \u2018Bio-inspired Robotics\u2019 course at the University of Washington, led by Prof. Sawyer Fuller, explores the realm of drawing inspiration from nature rather than reinventing the wheel. It covers various robots inspired by creatures capable of swimming, walking, hopping, and of course, flying. Lab assignments in this course involve working with a Crazyflie drone. Link: https://faculty.washington.edu/minster/bio_inspired_robotics/ Brown University offers a course called \u2018Introduction to Robotics\u2019 taught by Prof. Stefanie Tellix. While the introduction covers generic robotics, the focus of the full course is on building and programming the Duckiedrone . The course dives straight into autonomy and also teaches students how to work with ROS . Link: https://cs.brown.edu/courses/cs1951r/ Princeton University have also decided to release their \u2018Intro to Robotics\u2019 lectures and materials for the public. It covers all from control and estimation, computer vision and planning. Also it offers lab assignments with the Crazyflie . Link: https://irom-lab.princeton.edu/intro-to-robotics/","title":"University courses on Aerial Robotics with open resources"},{"location":"education_and_tutorial/#youtube","text":"Youtube also has quite some tutorials available so this section highlights a few. Drone Programming with Python : This popular tutorial/course teaches viewers how to program a real drone using Python with the DJI Tello . It offers a great opportunity for anyone looking for a short and enjoyable project to undertake, especially on a rainy day, while still working with a real platform. Link: https://youtu.be/LmEcyQnfpDA Intelligent Quads YouTube Channel : This channel is entirely dedicated to creating autonomous UAVs, covering topics from Ardupilot to MAVlink to ROS and Gazebo. It appears to be a valuable resource for beginners in the field of autonomous UAVs. This also includes ROS as part of the lessons as well. Link: https://www.youtube.com/@IntelligentQuads","title":"Youtube"},{"location":"education_and_tutorial/#code-examples","text":"Here are some code examples that can be used as reference for experiments. Mambo ROS Examples: This is a collection of experiments targeted Parrot Mambo drones, there are experiments with one or multiple vehicles at the same time. It runs over ROS over BLE, and some test are adapted to make use of a Vicon MoCap system. From a control theory's perspective, it showcases an optional robust control strategy, using an H-Infinity controller with perturbation estimation and a identified dynamic model of a Parrot Mambo drone. Link: https://github.com/TOTON95/Mambo_ROS_Examples","title":"Code Examples"},{"location":"education_and_tutorial/#some-special-mentions","text":"So here there are some courses that either doesn't fit in the above categories or are deprecated. University of Twente UAV Centre: The University of Twente has created a portal with a variety of UAV-related courses. You can find a wealth of information and educational materials on their website. Link: https://www.itc.nl/facilities/centres-of-expertise/uav-centre/ Self-Driving Car Specialization: If you are interested in learning more about SLAM (Simultaneous Localization and Mapping) and sensors, this specialization is tailored for self-driving cars but the theory can be useful for drones as well. Link: https://www.coursera.org/specializations/self-driving-cars Autonomous Navigation for Flying Robots: This older course is still highly relevant for anyone interested in autonomous navigation for flying robots. It offers valuable insights and knowledge. Link: https://www.edx.org/course/autonomous-navigation-for-flying-robots Drone Dojo: For those looking to build their own drones, Drone Dojo provides useful instructions and courses to get started on DIY drone projects. Link: https://dojofordrones.com/ Bachelor Majors in UAV Engineering: If you are fully committed to pursuing a career in aerial robotics, both Embry-Riddle Aeronautical University and the University of North Dakota offer full bachelor\u2019s majors in becoming a UAV engineer. Embry-Riddle Aeronautical University: https://erau.edu/degrees/bachelor/unmanned-aircraft-systems University of North Dakota: https://und.edu/programs/unmanned-aircraft-system-operations-bs-aero/","title":"Some special mentions"},{"location":"education_and_tutorial/#working-list","text":"This list contains some resources that we haven't included in the overview. Remove the item once it has been included PX4 getting started page Learning ArduPilot Aerial robotics 101 medium article Aerial robotics with ROS (work in progress) Bitcraze crazyflie tutorial page Simnet + Ardupilot academy Autonomy course Worcester Polytechnic Institute List of robotic aerial resources","title":"Working list"},{"location":"education_and_tutorial/#credit","text":"Lots of thanks for anybody contributing to this linkedin post . This was extremely helpful!","title":"Credit"},{"location":"hardware/","text":"Hardware, Components, and Dev Kits This is an list of development platforms for aerial robotics. Please start a pull request if you'd like to update these. Standard Commercial Research Platforms These are platforms that are currently commercially available for anybody to buy for their research. Copters Holybro: Holybro X500 V2 - PX4 Developer Kit PX4 Vision Dev Kit V1.5 ModalAI: PX4 Autonomy Dev Kit Starling 2 and Starling 2 Max Crazyflie 2.1 - Bitcraze NXP HoverGames Kit official hardware for the yearly HoverGames Challenge Duckietown: Duckiedrone DD21 Duckiedrone DD24 Clover by Coex PX4 Autonomy Developer Kit by ModelAI Droneblocks DEXI 5 3DR Quad Zero Kit Flapping wing Flapper Nimble+ insect-inspired UAV by Flapper Drones Industrial Platforms Uvify IFO-S Tricopter voliro AG DJI M300 Inhouse-developed platforms These are platforms that are standard within a lab or department, with information of what it contains provided with perhaps build instructions., Agilicous - University of Zurich ModQuad - Lehigh University RMF-Owl - Norwegian University of Science and Technology MiniHawk-VTOL Discontinued Platforms DJI M100 DJI tello Components Many of the UAVs are usually built by hand and composed of different components. This usually consists of a drone frame, flight controller boards, companion computers and of course motors, batteries and ESCs. Drone Frames Many drone frames are usually built from carbon fiber and custom-made for application or research. There are some frames that are provided that will provide some base: - DJI Flame wheel ARF kit F550, F450, F330 - Momentum Drones DEV-7 Flight controllers Holybro Pixhawk 4 Holybro Pixhawk 6C Holybro Pixhawk 6X Holybro Pixhawk 6X PRO CUAV's Pixhawk V6x mRobotics/3DR mRo PixRacer R15 discontinued, go look at: mRo PixRacerPro 3DR Control Zero Classic 3DR Control Zero H7 OEM 3DR Reference Design Carrier Board 3DR \"Stick\" Adapter (Carrier Board) Crazyflie Bolt 1.1 ARK Electronics ARK Electronics ARKV6X ARK Electronics Pi6X Flow Companion Computers For the drones that can carry it, the companion computers are important since they can do additional computations that the flight controller can not easily do. As these are capable of running some form of Linux, these can handle for instance computer vision with OpenCV or run nodes with ROS . Some companion computers also integrate flight control (RTOS) hardware in the same package Nvidia Jetson Xavier or the TX2 Module Nvidia Jetson Orin Intel Nuc Boards Raspberry PI 3 (A+) or Raspberry Pi 4 Khadas Vim3 Odroid (various boards) NXP NAVQPlus Qualcomm RB5 MRD5165 Eagle Kit (coming soon) VOXL 2 by Model AI EchoPilot AI AMD Xilinx Kria Starter Kits LattePanda x86 boards Carrier boards Several vendors have developed carrier boards that can expose input/output ports of companion computers mentioned above which are packaged in a System-on-Module (SoM) form factor and also offer a standard interface for plugging in popular flight controllers/their own FCs. Mistral MRD5165 Eagle based on Qualcomm RB5 ARK Electronics Jetson PAB carrier ARK Electronics Pi6X Flow Holybro Jetson Baseboard Dronee Lychee Drone autopilot hardware Airvolute DroneCore2 Jetson + Cube Depth Cameras Intel RealSense T265 Discontinued, look at: RealSense D455 RealSense D435i Oak-d Series like OAK-D Pro or OAK-D-Lite VOXL CAM by ModelAI Monocular Cameras Raspberry PI Cameras Compatible with RPI. IMX219 and IMX477 based cameras compatible with Jetson Xavier, NX, Nano, Orin series (other models may require device tree overlays or source changes). Google Coral Camera Compatible with NXP NAVQPLUS TOF Cameras Liteon A65 Camera Starter Kit Check with vendor for NXP NAVQPLUS compatibility. PMD Flexx2 3D Camera USB version should be compatible with most companion computers. VOXL2 TOF Depth Sensor Compatible with VOXL2. Check with vendor for early access product. Reference Bill of Materials Holybro S500v2 The Holybro S500v2 is a popular, relatively low-cost quadcopter. This is a list of the parts used with details of battery, motors, ESCs, and propellers with reference links to guide custom builds. S.No Part Name Part category Description Price (USD) Qty Total Cost (USD) Official/Reference Link 1 Holybro S500 frame Frame With landing gear, 385x385mm 42 1 42 https://holybro.com/collections/s500/products/s500-v2-kit?variant=42724497391805 2 Holybro Pixhawk 6C + GPS + Power module FC + GPS + Power module PM02 power module, M9N GPS 290 1 290 https://holybro.com/products/pixhawk-6c?variant=43005243785405 3 Holybro 2216 920KV CW Motor 19x19 mounting clockwise rotation 20 2 40 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094608061 4 Holybro 2216 920KV CCW Motor 19x19 mounting counter-clockwise rotation 20 2 40 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094640829 5 BLHeli S 20A ESC ESC Electronic Speed Controller to drive motors 14 4 56 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094706365 6 1045 propellers Props 10x4.5\" kit of 2 pairs 12 1 12 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094313149 7 Radiomaster R81 receiver Radio receiver Used for manually flying drone Line of Sight/testing* 18 1 18 https://holybro.com/products/radiomaster-r81-receiver 8 Holybro SiK telemetry radio v3 Telemetry link radio 500mW, 433MHz variant, pair of transmitter + receiver** 63 1 63 https://holybro.com/products/sik-telemetry-radio-v3?variant=42801817485501 9 Tattu 5200mAh 4S Battery 4S1P XT60 plug 35C 63 1 63 https://genstattu.com/tattu-5200mah-14-8v-35c-4s1p-lipo-battery-pack-with-xt60-plug.html Grand Total 624 Notes : *It can be used with Radiomaster Multiprotocol (4 in 1) or CC2500 based Radio Controller like FrSky Taranis X9D or similar **Used for connecting to ground control station, 915MHz variant also available Useful tool for this page : https://tabletomarkdown.com/convert-spreadsheet-to-markdown/","title":"Hardware, Components, and Dev Kits"},{"location":"hardware/#hardware-components-and-dev-kits","text":"This is an list of development platforms for aerial robotics. Please start a pull request if you'd like to update these.","title":"Hardware, Components, and Dev Kits"},{"location":"hardware/#standard-commercial-research-platforms","text":"These are platforms that are currently commercially available for anybody to buy for their research.","title":"Standard Commercial Research Platforms"},{"location":"hardware/#copters","text":"Holybro: Holybro X500 V2 - PX4 Developer Kit PX4 Vision Dev Kit V1.5 ModalAI: PX4 Autonomy Dev Kit Starling 2 and Starling 2 Max Crazyflie 2.1 - Bitcraze NXP HoverGames Kit official hardware for the yearly HoverGames Challenge Duckietown: Duckiedrone DD21 Duckiedrone DD24 Clover by Coex PX4 Autonomy Developer Kit by ModelAI Droneblocks DEXI 5 3DR Quad Zero Kit","title":"Copters"},{"location":"hardware/#flapping-wing","text":"Flapper Nimble+ insect-inspired UAV by Flapper Drones","title":"Flapping wing"},{"location":"hardware/#industrial-platforms","text":"Uvify IFO-S Tricopter voliro AG DJI M300","title":"Industrial Platforms"},{"location":"hardware/#inhouse-developed-platforms","text":"These are platforms that are standard within a lab or department, with information of what it contains provided with perhaps build instructions., Agilicous - University of Zurich ModQuad - Lehigh University RMF-Owl - Norwegian University of Science and Technology MiniHawk-VTOL","title":"Inhouse-developed platforms"},{"location":"hardware/#discontinued-platforms","text":"DJI M100 DJI tello","title":"Discontinued Platforms"},{"location":"hardware/#components","text":"Many of the UAVs are usually built by hand and composed of different components. This usually consists of a drone frame, flight controller boards, companion computers and of course motors, batteries and ESCs.","title":"Components"},{"location":"hardware/#drone-frames","text":"Many drone frames are usually built from carbon fiber and custom-made for application or research. There are some frames that are provided that will provide some base: - DJI Flame wheel ARF kit F550, F450, F330 - Momentum Drones DEV-7","title":"Drone Frames"},{"location":"hardware/#flight-controllers","text":"Holybro Pixhawk 4 Holybro Pixhawk 6C Holybro Pixhawk 6X Holybro Pixhawk 6X PRO CUAV's Pixhawk V6x mRobotics/3DR mRo PixRacer R15 discontinued, go look at: mRo PixRacerPro 3DR Control Zero Classic 3DR Control Zero H7 OEM 3DR Reference Design Carrier Board 3DR \"Stick\" Adapter (Carrier Board) Crazyflie Bolt 1.1 ARK Electronics ARK Electronics ARKV6X ARK Electronics Pi6X Flow","title":"Flight controllers"},{"location":"hardware/#companion-computers","text":"For the drones that can carry it, the companion computers are important since they can do additional computations that the flight controller can not easily do. As these are capable of running some form of Linux, these can handle for instance computer vision with OpenCV or run nodes with ROS . Some companion computers also integrate flight control (RTOS) hardware in the same package Nvidia Jetson Xavier or the TX2 Module Nvidia Jetson Orin Intel Nuc Boards Raspberry PI 3 (A+) or Raspberry Pi 4 Khadas Vim3 Odroid (various boards) NXP NAVQPlus Qualcomm RB5 MRD5165 Eagle Kit (coming soon) VOXL 2 by Model AI EchoPilot AI AMD Xilinx Kria Starter Kits LattePanda x86 boards","title":"Companion Computers"},{"location":"hardware/#carrier-boards","text":"Several vendors have developed carrier boards that can expose input/output ports of companion computers mentioned above which are packaged in a System-on-Module (SoM) form factor and also offer a standard interface for plugging in popular flight controllers/their own FCs. Mistral MRD5165 Eagle based on Qualcomm RB5 ARK Electronics Jetson PAB carrier ARK Electronics Pi6X Flow Holybro Jetson Baseboard Dronee Lychee Drone autopilot hardware Airvolute DroneCore2 Jetson + Cube","title":"Carrier boards"},{"location":"hardware/#depth-cameras","text":"Intel RealSense T265 Discontinued, look at: RealSense D455 RealSense D435i Oak-d Series like OAK-D Pro or OAK-D-Lite VOXL CAM by ModelAI","title":"Depth Cameras"},{"location":"hardware/#monocular-cameras","text":"Raspberry PI Cameras Compatible with RPI. IMX219 and IMX477 based cameras compatible with Jetson Xavier, NX, Nano, Orin series (other models may require device tree overlays or source changes). Google Coral Camera Compatible with NXP NAVQPLUS","title":"Monocular Cameras"},{"location":"hardware/#tof-cameras","text":"Liteon A65 Camera Starter Kit Check with vendor for NXP NAVQPLUS compatibility. PMD Flexx2 3D Camera USB version should be compatible with most companion computers. VOXL2 TOF Depth Sensor Compatible with VOXL2. Check with vendor for early access product.","title":"TOF Cameras"},{"location":"hardware/#reference-bill-of-materials","text":"","title":"Reference Bill of Materials"},{"location":"hardware/#holybro-s500v2","text":"The Holybro S500v2 is a popular, relatively low-cost quadcopter. This is a list of the parts used with details of battery, motors, ESCs, and propellers with reference links to guide custom builds. S.No Part Name Part category Description Price (USD) Qty Total Cost (USD) Official/Reference Link 1 Holybro S500 frame Frame With landing gear, 385x385mm 42 1 42 https://holybro.com/collections/s500/products/s500-v2-kit?variant=42724497391805 2 Holybro Pixhawk 6C + GPS + Power module FC + GPS + Power module PM02 power module, M9N GPS 290 1 290 https://holybro.com/products/pixhawk-6c?variant=43005243785405 3 Holybro 2216 920KV CW Motor 19x19 mounting clockwise rotation 20 2 40 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094608061 4 Holybro 2216 920KV CCW Motor 19x19 mounting counter-clockwise rotation 20 2 40 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094640829 5 BLHeli S 20A ESC ESC Electronic Speed Controller to drive motors 14 4 56 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094706365 6 1045 propellers Props 10x4.5\" kit of 2 pairs 12 1 12 https://holybro.com/products/spare-parts-s500-v2-kit?variant=41591094313149 7 Radiomaster R81 receiver Radio receiver Used for manually flying drone Line of Sight/testing* 18 1 18 https://holybro.com/products/radiomaster-r81-receiver 8 Holybro SiK telemetry radio v3 Telemetry link radio 500mW, 433MHz variant, pair of transmitter + receiver** 63 1 63 https://holybro.com/products/sik-telemetry-radio-v3?variant=42801817485501 9 Tattu 5200mAh 4S Battery 4S1P XT60 plug 35C 63 1 63 https://genstattu.com/tattu-5200mah-14-8v-35c-4s1p-lipo-battery-pack-with-xt60-plug.html Grand Total 624 Notes : *It can be used with Radiomaster Multiprotocol (4 in 1) or CC2500 based Radio Controller like FrSky Taranis X9D or similar **Used for connecting to ground control station, 915MHz variant also available Useful tool for this page : https://tabletomarkdown.com/convert-spreadsheet-to-markdown/","title":"Holybro S500v2"},{"location":"message_standards/","text":"Message standards REP 147 A Standard interface for Aerial Vehicles Within the ROS ecoysystem, there is currently a ROS enhancement proposal (REP) available to give guidance to message standards for UAVS. This can be found here: REP 147 A Standard interface for Aerial Vehicles Message standards within autopilot suites MAVlink MAVLink, an acronym for Micro Air Vehicle Link, is a communication system mainly used for the exchange of information between unmanned aerial vehicles and ground control stations. This protocol, which was launched in 2009, is structured as a header-only message marshaling library. MAVLink is versatile, supporting a broad range of messages and capable of being sent over virtually any type of serial connection, including Wi-Fi and radio technologies. In terms of messages, they are defined at compile time in XML files, which are processed to create libraries for sending and receiving messages. If new messages are added or existing ones are modified, the XML definitions need to be updated and the application recompiled. https://mavlink.io/en/ MAVlink is used in 2 autopilot suites. Eventhough the same message type are being shared in both the suites, the accomendating behavior might differ: Ardupilot MAVlink usage PX4 MAVlink usage","title":"Message standards"},{"location":"message_standards/#message-standards","text":"","title":"Message standards"},{"location":"message_standards/#rep-147-a-standard-interface-for-aerial-vehicles","text":"Within the ROS ecoysystem, there is currently a ROS enhancement proposal (REP) available to give guidance to message standards for UAVS. This can be found here: REP 147 A Standard interface for Aerial Vehicles","title":"REP 147 A Standard interface for Aerial Vehicles"},{"location":"message_standards/#message-standards-within-autopilot-suites","text":"","title":"Message standards within autopilot suites"},{"location":"message_standards/#mavlink","text":"MAVLink, an acronym for Micro Air Vehicle Link, is a communication system mainly used for the exchange of information between unmanned aerial vehicles and ground control stations. This protocol, which was launched in 2009, is structured as a header-only message marshaling library. MAVLink is versatile, supporting a broad range of messages and capable of being sent over virtually any type of serial connection, including Wi-Fi and radio technologies. In terms of messages, they are defined at compile time in XML files, which are processed to create libraries for sending and receiving messages. If new messages are added or existing ones are modified, the XML definitions need to be updated and the application recompiled. https://mavlink.io/en/ MAVlink is used in 2 autopilot suites. Eventhough the same message type are being shared in both the suites, the accomendating behavior might differ: Ardupilot MAVlink usage PX4 MAVlink usage","title":"MAVlink"},{"location":"middleware_and_drivers/","text":"Middleware and Drivers The aim for this page is to provide a collection of ROS packages/related libraries which are very useful for aerial ROS projects either to serve as a reference or directly use as a part of a custom software stack. This list aims to address the gap between the flight controller firmware and purely autonomy related packages. Middleware libraries Enabling low overhead publish/subscribe on microcontrollers: Micro-XRCE-DDS Zenoh PX4-FastRTPS - superceded by Micro-XRCE-DDS (https://docs.px4.io/main/en/middleware/uxrce_dds.html) Driver packages for drone platforms ROS packages built atop SDKs from drone vendors to interface to their closed-source flight controller firmwares. Several of these may be for much older ROS1 distros but can have utility in terms of serving as references. Parrot ARDrone Autonomy Parrot Bebop Autonomy DJI Tello driver Parrot Mambo driver","title":"Middleware and Drivers"},{"location":"middleware_and_drivers/#middleware-and-drivers","text":"The aim for this page is to provide a collection of ROS packages/related libraries which are very useful for aerial ROS projects either to serve as a reference or directly use as a part of a custom software stack. This list aims to address the gap between the flight controller firmware and purely autonomy related packages.","title":"Middleware and Drivers"},{"location":"middleware_and_drivers/#middleware-libraries","text":"Enabling low overhead publish/subscribe on microcontrollers: Micro-XRCE-DDS Zenoh PX4-FastRTPS - superceded by Micro-XRCE-DDS (https://docs.px4.io/main/en/middleware/uxrce_dds.html)","title":"Middleware libraries"},{"location":"middleware_and_drivers/#driver-packages-for-drone-platforms","text":"ROS packages built atop SDKs from drone vendors to interface to their closed-source flight controller firmwares. Several of these may be for much older ROS1 distros but can have utility in terms of serving as references. Parrot ARDrone Autonomy Parrot Bebop Autonomy DJI Tello driver Parrot Mambo driver","title":"Driver packages for drone platforms"},{"location":"safety_management/","text":"Safety and Management Systems Quadcopter and other Aerial vehicles come in all forms and sizes. Safety systems are important for all, but the bigger an aerial vehicle becomes, the more important it becomes that the right fail-safes and emergency systems are in place! This pages gives an overview of those safety systems that have been implemented so far. Safety in ROS Currently specifically for aerial vehicles, the safety implementation is depended on the ROS autonomy stack used. The ROS-0147 has a suggestion for flightmodes for a statemachine that can simplify the understanding of it. It is also expecting that ROS will be run offboard on an external computer, and that it should be in control of the safety state machine. This should probably be discussed if it would be a good idea for ROS to be in control of this or the autopilot suites themselves. Safety in Autopilot suites Adapted from the following blogpost: https://www.bitcraze.io/2023/04/safety-and-the-brushless/ These are current Safety managements systems existing in Paparazzi UAV , Betaflight , ArduPilot and PX4 . The Crazyflie ecosystem also have some measures but are currently overhauling their safety framework now in the form of a supervisor. Pre-flight checks. Before a vehicle can fly, certain conditions must be met. These includ: calibrating and ensuring functionality of internal sensors (IMU, barometer, magnetometer) receiving a GPS signal converging the internal state estimator (usually an extended Kalman filter) to a position checking for remote control connection and datalink to a ground station conducting feasibility checks (e.g., mission parameters, start location proximity) confirming sufficient battery level, and ensuring the absence of error states from previous flights or crashes. Preflight checks documentation: PX4: https://docs.px4.io/main/en/flying/pre_flight_checks.html#preflight-sensor-estimator-checks ArduPilot: https://ardupilot.org/copter/docs/common-prearm-safety-checks.html#failure-messages Beta flight: https://betaflight.com/docs/wiki/archive/GPS-Rescue-v4-4#sanity-check-options Paparazzi UAV: Indicated per platform if necessary, on their wiki: https://wiki.paparazziuav.org/wiki/Failsafe Crazyflie firmware: https://www.bitcraze.io/documentation/repository/crazyflie-firmware/master/functional-areas/supervisor/ Fail-safe mechanisms After passing pre-flight checks and arming the UAV, the takeoff command is given. However, UAV flights have inherent risks, particularly during takeoff. To mitigate these risks, numerous safety features, known as failsafes, are implemented during the flight phase. These failsafes are categorized as triggers and behaviors, allowing developers to specify the UAV's response to different failures, such as initiating a safe landing in the event of GPS loss. Triggers Thus, there are triggers that can enable the autopilot\u2019s failsafe mechanics: No connection with the remote control No connection with the Ground station or Datalink Low Battery Position estimate diverges or full GPS loss Waypoint going beyond geofence or Mission is not feasible Other vehicles are nearby. Also, sometimes the support of an external Automatic Trigger system is required, which is a box that monitors the conditions where the UAV should take action in case there is no GPS, other aerial vehicles are nearby, or the UAV is crossing a geofence determined by outdoor flight restrictions. Note that all of these triggers usually have a couple of conditions attached, such as the level of the \u2018low battery\u2019 or the number of seconds of \u2018GPS loss\u2019 deemed acceptable. Fail-safe behaviors During UAV flights, safety features can be customized per trigger, deviating from the default actions set by regulations. Disarming the vehicle completely increases the risk of crashing and causing harm. Allowing the drone to autonomously complete the mission without intervention poses the risk of losing the vehicle or trespassing restricted areas. Modifying default behaviors should be undertaken by knowledgeable individuals with careful consideration. These behaviors can include the following: No action at all Warning on the console or remote control display Continue the mission autonomously Stay still at the same position or go to a home position Fly to a lower altitude Land based on position or safely land by reducing thrust No input to motors or completely disarming the motors Fail-safe documentation PX4: https://docs.px4.io/main/en/config/safety.html ArduPilot: https://ardupilot.org/copter/docs/failsafe-landing-page.html Betaflight: https://betaflight.com/docs/development/Failsafe Paparazzi UAV: https://wiki.paparazziuav.org/wiki/Failsafe Crazyflie firmware: https://www.bitcraze.io/documentation/repository/crazyflie-firmware/master/functional-areas/supervisor/ Emergencies Fail-safes ensure safe flight, but emergencies like crashes, flips, or hardware failures can still occur. In such cases, the standard default action is to disarm the vehicle to prevent unintended motor activation. Backup systems connected to ESCs may take over if the autopilot becomes unresponsive. The pilot plays a vital role in safety, with the remote control featuring a dedicated button or switch for different modes, enabling actions like landing or disarming. It's recommended to have a net or towel to stop spinning motors and to promptly disconnect the battery. Being prepared for potential LiPo battery hazards is essential, with sand or fire retardant on hand. While autopilots provide guidance, conducting thorough research on handling emergencies, spinning parts, and LiPo battery fires is crucial. Here a list of that: * Remote control should have a dedicated button/switch for different modes, landing, or disarming. * Dealing with spinning motors Use a net or towel to stop them and promptly disconnect the battery. * To prepare for LiPo battery hazards, Have sand or fire retardant available.","title":"Safety and Management Systems"},{"location":"safety_management/#safety-and-management-systems","text":"Quadcopter and other Aerial vehicles come in all forms and sizes. Safety systems are important for all, but the bigger an aerial vehicle becomes, the more important it becomes that the right fail-safes and emergency systems are in place! This pages gives an overview of those safety systems that have been implemented so far.","title":"Safety and Management Systems"},{"location":"safety_management/#safety-in-ros","text":"Currently specifically for aerial vehicles, the safety implementation is depended on the ROS autonomy stack used. The ROS-0147 has a suggestion for flightmodes for a statemachine that can simplify the understanding of it. It is also expecting that ROS will be run offboard on an external computer, and that it should be in control of the safety state machine. This should probably be discussed if it would be a good idea for ROS to be in control of this or the autopilot suites themselves.","title":"Safety in ROS"},{"location":"safety_management/#safety-in-autopilot-suites","text":"Adapted from the following blogpost: https://www.bitcraze.io/2023/04/safety-and-the-brushless/ These are current Safety managements systems existing in Paparazzi UAV , Betaflight , ArduPilot and PX4 . The Crazyflie ecosystem also have some measures but are currently overhauling their safety framework now in the form of a supervisor.","title":"Safety in Autopilot suites"},{"location":"safety_management/#pre-flight-checks","text":"Before a vehicle can fly, certain conditions must be met. These includ: calibrating and ensuring functionality of internal sensors (IMU, barometer, magnetometer) receiving a GPS signal converging the internal state estimator (usually an extended Kalman filter) to a position checking for remote control connection and datalink to a ground station conducting feasibility checks (e.g., mission parameters, start location proximity) confirming sufficient battery level, and ensuring the absence of error states from previous flights or crashes. Preflight checks documentation: PX4: https://docs.px4.io/main/en/flying/pre_flight_checks.html#preflight-sensor-estimator-checks ArduPilot: https://ardupilot.org/copter/docs/common-prearm-safety-checks.html#failure-messages Beta flight: https://betaflight.com/docs/wiki/archive/GPS-Rescue-v4-4#sanity-check-options Paparazzi UAV: Indicated per platform if necessary, on their wiki: https://wiki.paparazziuav.org/wiki/Failsafe Crazyflie firmware: https://www.bitcraze.io/documentation/repository/crazyflie-firmware/master/functional-areas/supervisor/","title":"Pre-flight checks."},{"location":"safety_management/#fail-safe-mechanisms","text":"After passing pre-flight checks and arming the UAV, the takeoff command is given. However, UAV flights have inherent risks, particularly during takeoff. To mitigate these risks, numerous safety features, known as failsafes, are implemented during the flight phase. These failsafes are categorized as triggers and behaviors, allowing developers to specify the UAV's response to different failures, such as initiating a safe landing in the event of GPS loss.","title":"Fail-safe mechanisms"},{"location":"safety_management/#triggers","text":"Thus, there are triggers that can enable the autopilot\u2019s failsafe mechanics: No connection with the remote control No connection with the Ground station or Datalink Low Battery Position estimate diverges or full GPS loss Waypoint going beyond geofence or Mission is not feasible Other vehicles are nearby. Also, sometimes the support of an external Automatic Trigger system is required, which is a box that monitors the conditions where the UAV should take action in case there is no GPS, other aerial vehicles are nearby, or the UAV is crossing a geofence determined by outdoor flight restrictions. Note that all of these triggers usually have a couple of conditions attached, such as the level of the \u2018low battery\u2019 or the number of seconds of \u2018GPS loss\u2019 deemed acceptable.","title":"Triggers"},{"location":"safety_management/#fail-safe-behaviors","text":"During UAV flights, safety features can be customized per trigger, deviating from the default actions set by regulations. Disarming the vehicle completely increases the risk of crashing and causing harm. Allowing the drone to autonomously complete the mission without intervention poses the risk of losing the vehicle or trespassing restricted areas. Modifying default behaviors should be undertaken by knowledgeable individuals with careful consideration. These behaviors can include the following: No action at all Warning on the console or remote control display Continue the mission autonomously Stay still at the same position or go to a home position Fly to a lower altitude Land based on position or safely land by reducing thrust No input to motors or completely disarming the motors Fail-safe documentation PX4: https://docs.px4.io/main/en/config/safety.html ArduPilot: https://ardupilot.org/copter/docs/failsafe-landing-page.html Betaflight: https://betaflight.com/docs/development/Failsafe Paparazzi UAV: https://wiki.paparazziuav.org/wiki/Failsafe Crazyflie firmware: https://www.bitcraze.io/documentation/repository/crazyflie-firmware/master/functional-areas/supervisor/","title":"Fail-safe behaviors"},{"location":"safety_management/#emergencies","text":"Fail-safes ensure safe flight, but emergencies like crashes, flips, or hardware failures can still occur. In such cases, the standard default action is to disarm the vehicle to prevent unintended motor activation. Backup systems connected to ESCs may take over if the autopilot becomes unresponsive. The pilot plays a vital role in safety, with the remote control featuring a dedicated button or switch for different modes, enabling actions like landing or disarming. It's recommended to have a net or towel to stop spinning motors and to promptly disconnect the battery. Being prepared for potential LiPo battery hazards is essential, with sand or fire retardant on hand. While autopilots provide guidance, conducting thorough research on handling emergencies, spinning parts, and LiPo battery fires is crucial. Here a list of that: * Remote control should have a dedicated button/switch for different modes, landing, or disarming. * Dealing with spinning motors Use a net or towel to stop them and promptly disconnect the battery. * To prepare for LiPo battery hazards, Have sand or fire retardant available.","title":"Emergencies"},{"location":"simulation/","text":"Simulation of Aerial Robotics Simulation is crucial when working with Unmanned Aerial Vehicles (UAVs). Testing different trajectories and control paradigms in a simulator before implementing them on the real platform ensures not only safety but also facilitates development. This page presents several simulator options for aerial robotics enthusiasts. Comparison The following simulators have their own integrated physics simulation and basic rendering capabilities. They are capable of simulating the aerodynamic forces necessary to keep UAVs airborne: For the following comparison, we have refered this article Cora A. Dimmig et al. \"Survey of Simulators for Aerial Robots\" arXiv preprint arXiv:2311.02296v2 (2024) Features List migh not be complete. If you see any error or missing components, feel free to open a PR or issue. Name Physics Engine Rendering Linux[^1] Windows[^1] MacOS[^1] Interface (S/H)ITL[^6] Active[^2] Hardware requirement[^3] Licence Open source[^4] Interest [^5] Gazebo ( RotorS , CrazyS , PX4 SITL ) ODE/ Bullet/ DART/ Simbody OGRE \u2713 ( \u2713 \u2713 \u2713 ) \u2731 ( \u2717 \u2717 \u2717) \u2713 ( \u2717 \u2717 \u2717 ) ROS 1/2, C++, RL PX4, ArduPilot, CF ^7 \u2713 ( \u2717 \u2731 \u2717 ) minimal/decent Apache 2.0 \u2713 High Gazebo Bullet/ DART/ TPE OGRE \u2713 \u2731 \u2713 ROS 1/2, C++, Python, RL PX4, ArduPilot, CF \u2713 minimal/decent Apache 2.0 \u2713 High Isaac ( Pegasus , Aerial Gym ) NVIDIA PhysX/ Flex Vulkan \u2713 \u2717 \u2717 ROS 1/2, Python, RL Pegasus: PX4 \u2713 high/demanding NVIDIA OMNIVERSE (BSD 3) \u2717 (\u2713 \u2713) User specific Webots ODE OpenGL \u2713 \u2713 \u2713 ROS 1/2, C/C++, Python, MATLAB, Java ArduPilot, CF \u2713 decent/high Apache 2.0 \u2713 Developing CoppeliaSim Bullet/ODE/Vortex/Newton/MuJoCo OpenGL \u2713 \u2713 \u2713 ROS 1/2, C/C++, Python, MATLAB, Java,Lua,Octave -- \u2713 decent/high GNU GPL/Commercial \u2731 Decent AIRsim NVIDIA PhysX Unreal,Unity \u2713 \u2713 \u2713 ROS 1, C++, Python, C#, Java,RL PX4, ArduPilot \u2717 medium/high MIT \u2713 Low Flightmare Ad hoc, Gazebo classic Unity \u2713 \u2717 \u2717 ROS 1, C++, RL -- \u2717 -- MIT \u2713 Low FlightGoggles Ad hoc Unity \u2713 \u2731 \u2717 ROS 1, C++ Motion capture \u2717 -- MIT \u2713 Unknown Gym-pybullet-drones Pybullet OpenGL \u2713 \u2731 \u2713 Python, RL Betaflight, CF \u2713 minimal/decent/high MIT (Pybullet: zlib ) \u2713 High RotorTM Ad hoc OpenGL \u2713 \u2717 \u2717 ROS 1, Python, MATLAB -- \u2713 -- GNU GPL \u2713 Unknown MATLAB UAV Toolbox MATLAB Unreal \u2713 \u2713 \u2713 ROS 2, MATLAB PX4 \u2713 -- Proprietary, Commercial \u2717 Unknown O3de NVIDIA PhysX/ NVIDIA Cloth/ AMD TressFX Atom \u2713 \u2713 \u2731 ROS 2[^8] , C++ unknown \u2713 decent/high Apache-2.0/MIT \u2713 Developing Drake ad hoc unknown \u2713 \u2717 \u2713 C++, Python, ROS 2 unknown \u2713 unknown BSD 3 \u2713 Developing Flightgear unknown unknown \u2713 \u2713 \u2713 C++ unknown \u2713 minimal/decent GNU-GPL \u2713 Low RealFlight unknown unknown \u2717 \u2713 \u2717 -- unknown \u2713 minimal/decent non-public \u2717 Low RotorPy ad hoc unknown \u2713 \u2713 \u2713 Python -- \u2713 minimal/decent MIT \u2713 Developing [^1]: \u2713: Full support, \u2731: Partial support, \u2717: No support [^2]: \u2713: Active and maintained, \u2731: Inactive but responding to issues/ PR, \u2717: Inactive for 2+ years [^3]: For a referance, a laptop running Intel i5 10th gen (or similar) with 8gb ddr4 ram and NVIDIA T100 4gb (or similar) are considered as minimal requirement. [^4]: \u2713: Yes, \u2731: Yes for non commercial use-case , \u2717: No [^5]: Usage in Aerial ROS/Robotics community according to several survey on Discourse and during the meetings. [^6]: (Software/Hardware) In The Loop [^8]: It seem under development and there is some docs out there. Vehicle types Simulator Multirotor (Basic) Multirotor (Drag) Multirotor (Wind) Fixed-wings Aerial Manipulators Swarms Cars Other vehicles Gazebo (Classic & New) \u2713 \u2713 \u2713 \u2713 \u2731 \u2731 \u2713 \u2713 Isaac (Pegasus, Aerial Gym) \u2713 \u2717(\u2713,\u2717) \u2717 \u2717 \u2717 \u2713 \u2713(\u2717,\u2717) \u2713(\u2717,\u2717) Webots \u2713 \u2717 \u2717 \u2717 \u2717 \u2731 \u2713 \u2713 CoppeliaSim \u2713 \u2713 \u2731 \u2717 \u2731 \u2731 \u2713 \u2713 AirSim \u2713 \u2713 \u2713 \u2717 \u2717 \u2731 \u2713 \u2717 Flightmare \u2713 \u2713 \u2717 \u2717 \u2717 \u2713 \u2717 \u2717 FlightGoggles \u2713 \u2713 \u2717 \u2717 \u2717 \u2717 \u2713 \u2717 gym-pybullet-drones \u2713 \u2713 \u2717 \u2717 \u2717 \u2713 \u2717 \u2717 RotorTM \u2713 \u2717 \u2717 \u2717 \u2713 \u2713 \u2717 \u2717 MATLAB UAV Toolbox \u2713 \u2713 \u2713 \u2713 \u2717 \u2731 \u2717 \u2717 O3de* ~ ? ? ? ? ? ~ ~ Drake* ? ? ? ? ? ? ? ? RotorPy* ~ ~ ~ \u2717 \u2717 ~ \u2717 \u2717 [ * ] : Unknown data. If you have information on specific topic, please comment bellow with the referance link. [ ~ ] : Yes according to my knowledge but it needs development. [ ? ] : Unknown [ \u2717 ] : No according to my research. [ \u2713 ] : Yes [ \u2731 ] : Yes. But not specifically designed for it [ \u2717 ] : No Sensor support TODO Flight dynamics models Some simulators mostly focus on creating accurate dynamics for aerial vehicles. Here are some options: JSBSim ( https://github.com/JSBSim-Team/jsbsim ) YASim ( https://wiki.flightgear.org/YASim ) More to be added! Available UAV Models Each simulator typically offers a range of ready-to-use aerial vehicle models: Gazebo : https://app.gazebosim.org/search;q=uav Webots : https://webots.cloud/proto?keyword=robot%2Fflying Autopilot Suites Several autopilot suites provide instructions for using simulators, often with Software-in-the-Loop (SITL) or Hardware-in-the-Loop (HITL) options: Ardupilot : https://ardupilot.org/copter/docs/common-simulation.html Betaflight : https://betaflight.com/docs/development/SITL#sitl-in-realflight-9 Crazyflie : https://www.bitcraze.io/documentation/tutorials/getting-started-with-simulation/ DJI : https://www.dji.com/se/simulator Paparazzi UAV : https://wiki.paparazziuav.org/wiki/Simulation PX4 : https://docs.px4.io/main/en/simulation/#simulation ROSflight : https://docs.rosflight.org/v1.3/user-guide/gazebo_simulation/","title":"Simulation of Aerial Robotics"},{"location":"simulation/#simulation-of-aerial-robotics","text":"Simulation is crucial when working with Unmanned Aerial Vehicles (UAVs). Testing different trajectories and control paradigms in a simulator before implementing them on the real platform ensures not only safety but also facilitates development. This page presents several simulator options for aerial robotics enthusiasts.","title":"Simulation of Aerial Robotics"},{"location":"simulation/#comparison","text":"The following simulators have their own integrated physics simulation and basic rendering capabilities. They are capable of simulating the aerodynamic forces necessary to keep UAVs airborne: For the following comparison, we have refered this article Cora A. Dimmig et al. \"Survey of Simulators for Aerial Robots\" arXiv preprint arXiv:2311.02296v2 (2024)","title":"Comparison"},{"location":"simulation/#features","text":"List migh not be complete. If you see any error or missing components, feel free to open a PR or issue. Name Physics Engine Rendering Linux[^1] Windows[^1] MacOS[^1] Interface (S/H)ITL[^6] Active[^2] Hardware requirement[^3] Licence Open source[^4] Interest [^5] Gazebo ( RotorS , CrazyS , PX4 SITL ) ODE/ Bullet/ DART/ Simbody OGRE \u2713 ( \u2713 \u2713 \u2713 ) \u2731 ( \u2717 \u2717 \u2717) \u2713 ( \u2717 \u2717 \u2717 ) ROS 1/2, C++, RL PX4, ArduPilot, CF ^7 \u2713 ( \u2717 \u2731 \u2717 ) minimal/decent Apache 2.0 \u2713 High Gazebo Bullet/ DART/ TPE OGRE \u2713 \u2731 \u2713 ROS 1/2, C++, Python, RL PX4, ArduPilot, CF \u2713 minimal/decent Apache 2.0 \u2713 High Isaac ( Pegasus , Aerial Gym ) NVIDIA PhysX/ Flex Vulkan \u2713 \u2717 \u2717 ROS 1/2, Python, RL Pegasus: PX4 \u2713 high/demanding NVIDIA OMNIVERSE (BSD 3) \u2717 (\u2713 \u2713) User specific Webots ODE OpenGL \u2713 \u2713 \u2713 ROS 1/2, C/C++, Python, MATLAB, Java ArduPilot, CF \u2713 decent/high Apache 2.0 \u2713 Developing CoppeliaSim Bullet/ODE/Vortex/Newton/MuJoCo OpenGL \u2713 \u2713 \u2713 ROS 1/2, C/C++, Python, MATLAB, Java,Lua,Octave -- \u2713 decent/high GNU GPL/Commercial \u2731 Decent AIRsim NVIDIA PhysX Unreal,Unity \u2713 \u2713 \u2713 ROS 1, C++, Python, C#, Java,RL PX4, ArduPilot \u2717 medium/high MIT \u2713 Low Flightmare Ad hoc, Gazebo classic Unity \u2713 \u2717 \u2717 ROS 1, C++, RL -- \u2717 -- MIT \u2713 Low FlightGoggles Ad hoc Unity \u2713 \u2731 \u2717 ROS 1, C++ Motion capture \u2717 -- MIT \u2713 Unknown Gym-pybullet-drones Pybullet OpenGL \u2713 \u2731 \u2713 Python, RL Betaflight, CF \u2713 minimal/decent/high MIT (Pybullet: zlib ) \u2713 High RotorTM Ad hoc OpenGL \u2713 \u2717 \u2717 ROS 1, Python, MATLAB -- \u2713 -- GNU GPL \u2713 Unknown MATLAB UAV Toolbox MATLAB Unreal \u2713 \u2713 \u2713 ROS 2, MATLAB PX4 \u2713 -- Proprietary, Commercial \u2717 Unknown O3de NVIDIA PhysX/ NVIDIA Cloth/ AMD TressFX Atom \u2713 \u2713 \u2731 ROS 2[^8] , C++ unknown \u2713 decent/high Apache-2.0/MIT \u2713 Developing Drake ad hoc unknown \u2713 \u2717 \u2713 C++, Python, ROS 2 unknown \u2713 unknown BSD 3 \u2713 Developing Flightgear unknown unknown \u2713 \u2713 \u2713 C++ unknown \u2713 minimal/decent GNU-GPL \u2713 Low RealFlight unknown unknown \u2717 \u2713 \u2717 -- unknown \u2713 minimal/decent non-public \u2717 Low RotorPy ad hoc unknown \u2713 \u2713 \u2713 Python -- \u2713 minimal/decent MIT \u2713 Developing [^1]: \u2713: Full support, \u2731: Partial support, \u2717: No support [^2]: \u2713: Active and maintained, \u2731: Inactive but responding to issues/ PR, \u2717: Inactive for 2+ years [^3]: For a referance, a laptop running Intel i5 10th gen (or similar) with 8gb ddr4 ram and NVIDIA T100 4gb (or similar) are considered as minimal requirement. [^4]: \u2713: Yes, \u2731: Yes for non commercial use-case , \u2717: No [^5]: Usage in Aerial ROS/Robotics community according to several survey on Discourse and during the meetings. [^6]: (Software/Hardware) In The Loop [^8]: It seem under development and there is some docs out there.","title":"Features"},{"location":"simulation/#vehicle-types","text":"Simulator Multirotor (Basic) Multirotor (Drag) Multirotor (Wind) Fixed-wings Aerial Manipulators Swarms Cars Other vehicles Gazebo (Classic & New) \u2713 \u2713 \u2713 \u2713 \u2731 \u2731 \u2713 \u2713 Isaac (Pegasus, Aerial Gym) \u2713 \u2717(\u2713,\u2717) \u2717 \u2717 \u2717 \u2713 \u2713(\u2717,\u2717) \u2713(\u2717,\u2717) Webots \u2713 \u2717 \u2717 \u2717 \u2717 \u2731 \u2713 \u2713 CoppeliaSim \u2713 \u2713 \u2731 \u2717 \u2731 \u2731 \u2713 \u2713 AirSim \u2713 \u2713 \u2713 \u2717 \u2717 \u2731 \u2713 \u2717 Flightmare \u2713 \u2713 \u2717 \u2717 \u2717 \u2713 \u2717 \u2717 FlightGoggles \u2713 \u2713 \u2717 \u2717 \u2717 \u2717 \u2713 \u2717 gym-pybullet-drones \u2713 \u2713 \u2717 \u2717 \u2717 \u2713 \u2717 \u2717 RotorTM \u2713 \u2717 \u2717 \u2717 \u2713 \u2713 \u2717 \u2717 MATLAB UAV Toolbox \u2713 \u2713 \u2713 \u2713 \u2717 \u2731 \u2717 \u2717 O3de* ~ ? ? ? ? ? ~ ~ Drake* ? ? ? ? ? ? ? ? RotorPy* ~ ~ ~ \u2717 \u2717 ~ \u2717 \u2717 [ * ] : Unknown data. If you have information on specific topic, please comment bellow with the referance link. [ ~ ] : Yes according to my knowledge but it needs development. [ ? ] : Unknown [ \u2717 ] : No according to my research. [ \u2713 ] : Yes [ \u2731 ] : Yes. But not specifically designed for it [ \u2717 ] : No","title":"Vehicle types"},{"location":"simulation/#sensor-support","text":"TODO","title":"Sensor support"},{"location":"simulation/#flight-dynamics-models","text":"Some simulators mostly focus on creating accurate dynamics for aerial vehicles. Here are some options: JSBSim ( https://github.com/JSBSim-Team/jsbsim ) YASim ( https://wiki.flightgear.org/YASim ) More to be added!","title":"Flight dynamics models"},{"location":"simulation/#available-uav-models","text":"Each simulator typically offers a range of ready-to-use aerial vehicle models: Gazebo : https://app.gazebosim.org/search;q=uav Webots : https://webots.cloud/proto?keyword=robot%2Fflying","title":"Available UAV Models"},{"location":"simulation/#autopilot-suites","text":"Several autopilot suites provide instructions for using simulators, often with Software-in-the-Loop (SITL) or Hardware-in-the-Loop (HITL) options: Ardupilot : https://ardupilot.org/copter/docs/common-simulation.html Betaflight : https://betaflight.com/docs/development/SITL#sitl-in-realflight-9 Crazyflie : https://www.bitcraze.io/documentation/tutorials/getting-started-with-simulation/ DJI : https://www.dji.com/se/simulator Paparazzi UAV : https://wiki.paparazziuav.org/wiki/Simulation PX4 : https://docs.px4.io/main/en/simulation/#simulation ROSflight : https://docs.rosflight.org/v1.3/user-guide/gazebo_simulation/","title":"Autopilot Suites"}]} \ No newline at end of file diff --git a/search/worker.js b/search/worker.js new file mode 100644 index 0000000..8628dbc --- /dev/null +++ b/search/worker.js @@ -0,0 +1,133 @@ +var base_path = 'function' === typeof importScripts ? '.' : '/search/'; +var allowSearch = false; +var index; +var documents = {}; +var lang = ['en']; +var data; + +function getScript(script, callback) { + console.log('Loading script: ' + script); + $.getScript(base_path + script).done(function () { + callback(); + }).fail(function (jqxhr, settings, exception) { + console.log('Error: ' + exception); + }); +} + +function getScriptsInOrder(scripts, callback) { + if (scripts.length === 0) { + callback(); + return; + } + getScript(scripts[0], function() { + getScriptsInOrder(scripts.slice(1), callback); + }); +} + +function loadScripts(urls, callback) { + if( 'function' === typeof importScripts ) { + importScripts.apply(null, urls); + callback(); + } else { + getScriptsInOrder(urls, callback); + } +} + +function onJSONLoaded () { + data = JSON.parse(this.responseText); + var scriptsToLoad = ['lunr.js']; + if (data.config && data.config.lang && data.config.lang.length) { + lang = data.config.lang; + } + if (lang.length > 1 || lang[0] !== "en") { + scriptsToLoad.push('lunr.stemmer.support.js'); + if (lang.length > 1) { + scriptsToLoad.push('lunr.multi.js'); + } + if (lang.includes("ja") || lang.includes("jp")) { + scriptsToLoad.push('tinyseg.js'); + } + for (var i=0; i < lang.length; i++) { + if (lang[i] != 'en') { + scriptsToLoad.push(['lunr', lang[i], 'js'].join('.')); + } + } + } + loadScripts(scriptsToLoad, onScriptsLoaded); +} + +function onScriptsLoaded () { + console.log('All search scripts loaded, building Lunr index...'); + if (data.config && data.config.separator && data.config.separator.length) { + lunr.tokenizer.separator = new RegExp(data.config.separator); + } + + if (data.index) { + index = lunr.Index.load(data.index); + data.docs.forEach(function (doc) { + documents[doc.location] = doc; + }); + console.log('Lunr pre-built index loaded, search ready'); + } else { + index = lunr(function () { + if (lang.length === 1 && lang[0] !== "en" && lunr[lang[0]]) { + this.use(lunr[lang[0]]); + } else if (lang.length > 1) { + this.use(lunr.multiLanguage.apply(null, lang)); // spread operator not supported in all browsers: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/Spread_operator#Browser_compatibility + } + this.field('title'); + this.field('text'); + this.ref('location'); + + for (var i=0; i < data.docs.length; i++) { + var doc = data.docs[i]; + this.add(doc); + documents[doc.location] = doc; + } + }); + console.log('Lunr index built, search ready'); + } + allowSearch = true; + postMessage({config: data.config}); + postMessage({allowSearch: allowSearch}); +} + +function init () { + var oReq = new XMLHttpRequest(); + oReq.addEventListener("load", onJSONLoaded); + var index_path = base_path + '/search_index.json'; + if( 'function' === typeof importScripts ){ + index_path = 'search_index.json'; + } + oReq.open("GET", index_path); + oReq.send(); +} + +function search (query) { + if (!allowSearch) { + console.error('Assets for search still loading'); + return; + } + + var resultDocuments = []; + var results = index.search(query); + for (var i=0; i < results.length; i++){ + var result = results[i]; + doc = documents[result.ref]; + doc.summary = doc.text.substring(0, 200); + resultDocuments.push(doc); + } + return resultDocuments; +} + +if( 'function' === typeof importScripts ) { + onmessage = function (e) { + if (e.data.init) { + init(); + } else if (e.data.query) { + postMessage({ results: search(e.data.query) }); + } else { + console.error("Worker - Unrecognized message: " + e); + } + }; +} diff --git a/simulation/index.html b/simulation/index.html new file mode 100644 index 0000000..e920ab8 --- /dev/null +++ b/simulation/index.html @@ -0,0 +1,654 @@ + + + + + + + +Simulation is crucial when working with Unmanned Aerial Vehicles (UAVs). Testing different trajectories and control paradigms in a simulator before implementing them on the real platform ensures not only safety but also facilitates development.
+This page presents several simulator options for aerial robotics enthusiasts.
+The following simulators have their own integrated physics simulation and basic rendering capabilities. They are capable of simulating the aerodynamic forces necessary to keep UAVs airborne:
+For the following comparison, we have refered this article
+++Cora A. Dimmig et al. "Survey of Simulators for Aerial Robots" arXiv preprint arXiv:2311.02296v2 (2024)
+
List migh not be complete. If you see any error or missing components, feel free to open a PR or issue.
+Name | +Physics Engine | +Rendering | +Linux[^1] | +Windows[^1] | +MacOS[^1] | +Interface | +(S/H)ITL[^6] | +Active[^2] | +Hardware requirement[^3] | +Licence | +Open source[^4] | +Interest [^5] | +
---|---|---|---|---|---|---|---|---|---|---|---|---|
Gazebo ( RotorS, CrazyS, PX4 SITL) |
+ODE/ Bullet/ DART/ Simbody | +OGRE | +✓ ( ✓ ✓ ✓ ) |
+✱ ( ✗ ✗ ✗) |
+✓ ( ✗ ✗ ✗ ) |
+ROS 1/2, C++, RL | +PX4, ArduPilot, CF^7 | +✓ ( ✗ ✱ ✗ ) |
+minimal/decent | +Apache 2.0 | +✓ | +High | +
Gazebo | +Bullet/ DART/ TPE | +OGRE | +✓ | +✱ | +✓ | +ROS 1/2, C++, Python, RL | +PX4, ArduPilot, CF | +✓ | +minimal/decent | +Apache 2.0 | +✓ | +High | +
Isaac ( Pegasus, Aerial Gym) |
+NVIDIA PhysX/ Flex | +Vulkan | +✓ | +✗ | +✗ | +ROS 1/2, Python, RL | +Pegasus: PX4 | +✓ | +high/demanding | +NVIDIA OMNIVERSE (BSD 3) |
+✗ (✓ ✓) |
+User specific | +
Webots | +ODE | +OpenGL | +✓ | +✓ | +✓ | +ROS 1/2, C/C++, Python, MATLAB, Java | +ArduPilot, CF | +✓ | +decent/high | +Apache 2.0 | +✓ | +Developing | +
CoppeliaSim | +Bullet/ODE/Vortex/Newton/MuJoCo | +OpenGL | +✓ | +✓ | +✓ | +ROS 1/2, C/C++, Python, MATLAB, Java,Lua,Octave | +-- | +✓ | +decent/high | +GNU GPL/Commercial | +✱ | +Decent | +
AIRsim | +NVIDIA PhysX | +Unreal,Unity | +✓ | +✓ | +✓ | +ROS 1, C++, Python, C#, Java,RL | +PX4, ArduPilot | +✗ | +medium/high | +MIT | +✓ | +Low | +
Flightmare | +Ad hoc, Gazebo classic | +Unity | +✓ | +✗ | +✗ | +ROS 1, C++, RL | +-- | +✗ | +-- | +MIT | +✓ | +Low | +
FlightGoggles | +Ad hoc | +Unity | +✓ | +✱ | +✗ | +ROS 1, C++ | +Motion capture | +✗ | +-- | +MIT | +✓ | +Unknown | +
Gym-pybullet-drones | +Pybullet | +OpenGL | +✓ | +✱ | +✓ | +Python, RL | +Betaflight, CF | +✓ | +minimal/decent/high | +MIT (Pybullet: zlib) | +✓ | +High | +
RotorTM | +Ad hoc | +OpenGL | +✓ | +✗ | +✗ | +ROS 1, Python, MATLAB | +-- | +✓ | +-- | +GNU GPL | +✓ | +Unknown | +
MATLAB UAV Toolbox | +MATLAB | +Unreal | +✓ | +✓ | +✓ | +ROS 2, MATLAB | +PX4 | +✓ | +-- | +Proprietary, Commercial | +✗ | +Unknown | +
O3de | +NVIDIA PhysX/ NVIDIA Cloth/ AMD TressFX | +Atom | +✓ | +✓ | +✱ | +ROS 2[^8] , C++ | +unknown | +✓ | +decent/high | +Apache-2.0/MIT | +✓ | +Developing | +
Drake | +ad hoc | +unknown | +✓ | +✗ | +✓ | +C++, Python, ROS 2 | +unknown | +✓ | +unknown | +BSD 3 | +✓ | +Developing | +
Flightgear | +unknown | +unknown | +✓ | +✓ | +✓ | +C++ | +unknown | +✓ | +minimal/decent | +GNU-GPL | +✓ | +Low | +
RealFlight | +unknown | +unknown | +✗ | +✓ | +✗ | +-- | +unknown | +✓ | +minimal/decent | +non-public | +✗ | +Low | +
RotorPy | +ad hoc | +unknown | +✓ | +✓ | +✓ | +Python | +-- | +✓ | +minimal/decent | +MIT | +✓ | +Developing | +
[^1]: ✓: Full support, ✱: Partial support, ✗: No support
+[^2]: ✓: Active and maintained, ✱: Inactive but responding to issues/ PR, ✗: Inactive for 2+ years
+[^3]: For a referance, a laptop running Intel i5 10th gen (or similar) with 8gb ddr4 ram and NVIDIA T100 4gb (or similar) are considered as minimal requirement.
+[^4]: ✓: Yes, ✱: Yes for non commercial use-case , ✗: No
+[^5]: Usage in Aerial ROS/Robotics community according to several survey on Discourse and during the meetings.
+[^6]: (Software/Hardware) In The Loop
+[^8]: It seem under development and there is some docs out there.
+Simulator | +Multirotor (Basic) | +Multirotor (Drag) | +Multirotor (Wind) | +Fixed-wings | +Aerial Manipulators | +Swarms | +Cars | +Other vehicles | +
---|---|---|---|---|---|---|---|---|
Gazebo (Classic & New) | +✓ | +✓ | +✓ | +✓ | +✱ | +✱ | +✓ | +✓ | +
Isaac (Pegasus, Aerial Gym) | +✓ | +✗(✓,✗) | +✗ | +✗ | +✗ | +✓ | +✓(✗,✗) | +✓(✗,✗) | +
Webots | +✓ | +✗ | +✗ | +✗ | +✗ | +✱ | +✓ | +✓ | +
CoppeliaSim | +✓ | +✓ | +✱ | +✗ | +✱ | +✱ | +✓ | +✓ | +
AirSim | +✓ | +✓ | +✓ | +✗ | +✗ | +✱ | +✓ | +✗ | +
Flightmare | +✓ | +✓ | +✗ | +✗ | +✗ | +✓ | +✗ | +✗ | +
FlightGoggles | +✓ | +✓ | +✗ | +✗ | +✗ | +✗ | +✓ | +✗ | +
gym-pybullet-drones | +✓ | +✓ | +✗ | +✗ | +✗ | +✓ | +✗ | +✗ | +
RotorTM | +✓ | +✗ | +✗ | +✗ | +✓ | +✓ | +✗ | +✗ | +
MATLAB UAV Toolbox | +✓ | +✓ | +✓ | +✓ | +✗ | +✱ | +✗ | +✗ | +
O3de* | +~ | +? | +? | +? | +? | +? | +~ | +~ | +
Drake* | +? | +? | +? | +? | +? | +? | +? | +? | +
RotorPy* | +~ | +~ | +~ | +✗ | +✗ | +~ | +✗ | +✗ | +
TODO
+Some simulators mostly focus on creating accurate dynamics for aerial vehicles. Here are some options:
+Each simulator typically offers a range of ready-to-use aerial vehicle models:
+Several autopilot suites provide instructions for using simulators, often with Software-in-the-Loop (SITL) or Hardware-in-the-Loop (HITL) options:
+