# Welcome to AirSim
AirSim is a simulator for drones, cars and more, built on [Unreal Engine](https://www.unrealengine.com/) (we now also have an experimental [Unity](https://unity3d.com/) release). It is open-source, cross platform, and supports hardware-in-loop with popular flight controllers such as PX4 for physically and visually realistic simulations. It is developed as an Unreal plugin that can simply be dropped into any Unreal environment. Similarly, we have an experimental release for a Unity plugin.
Our goal is to develop AirSim as a platform for AI research to experiment with deep learning, computer vision and reinforcement learning algorithms for autonomous vehicles. For this purpose, AirSim also exposes APIs to retrieve data and control vehicles in a platform independent way.
**Check out the quick 1.5 minute demo**
Drones in AirSim
[![AirSim Drone Demo Video](docs/images/demo_video.png)](https://youtu.be/-WfTr1-OBGQ)
Cars in AirSim
[![AirSim Car Demo Video](docs/images/car_demo_video.png)](https://youtu.be/gnz1X3UNM5Y)
## What's New
* Added Weather Effects and [APIs](https://microsoft.github.io/AirSim/docs/apis#weather-apis)
* Added [Time of Day API](https://microsoft.github.io/AirSim/docs/apis#time-of-day-api)
* An experimental integration of [AirSim on Unity](https://github.com/Microsoft/AirSim/tree/master/Unity) is now available. Learn more in [Unity blog post](https://blogs.unity3d.com/2018/11/14/airsim-on-unity-experiment-with-autonomous-vehicle-simulation).
* [New environments](https://github.com/Microsoft/AirSim/releases/tag/v1.2.1): Forest, Plains (windmill farm), TalkingHeads (human head simulation), TrapCam (animal detection via camera)
* Highly efficient [NoDisplay view mode](https://microsoft.github.io/AirSim/docs/settings#viewmode) to turn off main screen rendering so you can capture images at high rate
* [Lidar Sensor](https://microsoft.github.io/AirSim/docs/lidar)
* Case Study: [Formula Student Technion Driverless](https://github.com/Microsoft/AirSim/wiki/technion)
* [Multi-Vehicle Capability](https://microsoft.github.io/AirSim/docs/multi_vehicle)
* [ROS publisher](https://github.com/Microsoft/AirSim/pull/1135)
For complete list of changes, view our [Changelog](CHANGELOG.md)
## How to Get It
### Windows
* [Download binaries](https://microsoft.github.io/AirSim/docs/use_precompiled)
* [Build it](https://microsoft.github.io/AirSim/docs/build_windows)
### Linux
* [Build it](https://microsoft.github.io/AirSim/docs/build_linux)
[![Build Status](https://travis-ci.org/Microsoft/AirSim.svg?branch=master)](https://travis-ci.org/Microsoft/AirSim)
## How to Use It
### Documentation
View our [detailed documentation](https://microsoft.github.io/AirSim/) on all aspects of AirSim.
### Manual drive
If you have remote control (RC) as shown below, you can manually control the drone in the simulator. For cars, you can use arrow keys to drive manually.
[More details](https://microsoft.github.io/AirSim/docs/remote_control/)
![record screenshot](docs/images/AirSimDroneManual.gif)
![record screenshot](docs/images/AirSimCarManual.gif)
### Programmatic control
AirSim exposes APIs so you can interact with the vehicle in the simulation programmatically. You can use these APIs to retrieve images, get state, control the vehicle and so on. The APIs are exposed through the RPC, and are accessible via a variety of languages, including C++, Python, C# and Java.
These APIs are also available as part of a separate, independent cross-platform library, so you can deploy them on a companion computer on your vehicle. This way you can write and test your code in the simulator, and later execute it on the real vehicles. Transfer learning and related research is one of our focus areas.
Note that you can use [SimMode setting](https://microsoft.github.io/AirSim/docs/settings#simmode) to specify the default vehicle or the new [ComputerVision mode](https://microsoft.github.io/AirSim/docs/image_apis#computer-vision-mode-1) so you don't get prompted each time you start AirSim.
[More details](https://microsoft.github.io/AirSim/docs/apis/)
### Gathering training data
There are two ways you can generate training data from AirSim for deep learning. The easiest way is to simply press the record button in the lower right corner. This will start writing pose and images for each frame. The data logging code is pretty simple and you can modify it to your heart's content.
![record screenshot](docs/images/record_data.png)
A better way to generate training data exactly the way you want is by accessing the APIs. This allows you to be in full control of how, what, where and when you want to log data.
### Computer Vision mode
Yet another way to use AirSim is the so-called "Computer Vision" mode. In this mode, you don't have vehicles or physics. You can use the keyboard to move around the scene, or use APIs to position available cameras in any arbitrary pose, and collect images such as depth, disparity, surface normals or object segmentation.
[More details](https://microsoft.github.io/AirSim/docs/docs/image_apis/)
### Weather Effects
Press F10 to see various options available for weather effects. You can also control the weather using [APIs](https://microsoft.github.io/AirSim/docs/apis#weather-apis). Press F1 to see other options available.
![record screenshot](docs/images/weather_menu.png)
## Tutorials
- [Video - Setting up AirSim with Pixhawk Tutorial](https://youtu.be/1oY8Qu5maQQ) by Chris Lovett
- [Video - Using AirSim with Pixhawk Tutorial](https://youtu.be/HNWdYrtw3f0) by Chris Lovett
- [Video - Using off-the-self environments with AirSim](https://www.youtube.com/watch?v=y09VbdQWvQY) by Jim Piavis
- [Reinforcement Learning with AirSim](https://microsoft.github.io/AirSim/docs/reinforcement_learning) by Ashish Kapoor
- [The Autonomous Driving Cookbook](https://aka.ms/AutonomousDrivingCookbook) by Microsoft Deep Learning and Robotics Garage Chapter
- [Using TensorFlow for simple collision avoidance](https://github.com/simondlevy/AirSimTensorFlow) by Simon Levy and WLU team
## Participate
### Paper
More technical details are available in [AirSim paper (FSR 2017 Conference)](https://arxiv.org/abs/1705.05065). Please cite this as:
```
@inproceedings{airsim2017fsr,
author = {Shital Shah and Debadeepta Dey and Chris Lovett and Ashish Kapoor},
title = {AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles},
year = {2017},
booktitle = {Field and Service Robotics},
eprint = {arXiv:1705.05065},
url = {https://arxiv.org/abs/1705.05065}
}
```
### Contribute
Please take a look at [open issues](https://github.com/microsoft/airsim/issues) if you are looking for areas to contribute to.
* [More on AirSim design](https://microsoft.github.io/AirSim/docs/design)
* [More on code structure](https://microsoft.github.io/AirSim/docs/code_structure)
* [Contribution Guidelines](CONTRIBUTING.md)
* [Trello Board](https://trello.com/b/1t2qCeaA/wishlist-by-community-for-community)
### Who is Using AirSim?
We are maintaining a [list](https://microsoft.github.io/AirSim/docs/who_is_using) of a few projects, people and groups that we are aware of. If you would like to be featured in this list please [make a request here](https://github.com/microsoft/airsim/issues).
## Contact
Join the AirSim group on [Facebook](https://www.facebook.com/groups/1225832467530667/) to stay up to date or ask any questions.
## FAQ
If you run into problems, check the [FAQ](https://microsoft.github.io/AirSim/docs/faq) and feel free to post issues in the [AirSim](https://github.com/Microsoft/AirSim/issues) repository.
## License
This project is released under the MIT License. Please review the [License file](LICENSE) for more details.
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
毕业设计是高等教育阶段学生完成学业的一个重要环节,通常在学士或硕士学业即将结束时进行。这是学生将在整个学业中所学知识和技能应用到实际问题上的机会,旨在检验学生是否能够独立思考、解决问题,并展示其专业能力的一项综合性任务。 毕业设计的主要特点包括: 独立性: 毕业设计要求学生具备独立思考和解决问题的能力。学生需要选择一个合适的课题,研究相关文献,进行实地调查或实验,并提出独立见解。 实践性: 毕业设计是将理论知识应用到实际问题中的一次实践。通过完成毕业设计,学生能够将所学的专业知识转化为实际的解决方案,加深对专业领域的理解。 综合性: 毕业设计往往要求学生运用多个学科的知识,综合各种技能。这有助于培养学生的综合素养,提高他们的综合能力。 导师指导: 学生在毕业设计过程中通常由一名指导老师或导师团队提供指导和支持。导师负责引导学生确定研究方向、制定计划、提供建议,并在整个过程中监督进展。 学术规范: 毕业设计要求学生按照学术规范完成研究,包括文献综述、研究设计、数据采集与分析、结论和讨论等环节。学生需要撰写一篇完整的毕业论文,并进行答辩。
资源推荐
资源详情
资源评论
收起资源包目录
实现了UE4和airsim环境下无人机自主导航和目标跟踪的强化学习算法.zip (646个子文件)
build_docs.bat 2KB
getData.bat 2KB
check_cmake.bat 1KB
update_mavlibkcom.bat 196B
clean_rebuild.bat 135B
references.bib 7KB
AirSim_FrSkyTaranis.bin 437B
spbasic.bst 32KB
spmpsci.bst 29KB
spphys.bst 28KB
svmult.cls 79KB
CommonSetup.cmake 6KB
build.cmd 8KB
clean.cmd 368B
main.cpp 56KB
MultirotorApiBase.cpp 27KB
main.cpp 17KB
RpcLibClientBase.cpp 14KB
RpcLibServerBase.cpp 13KB
SafetyEval.cpp 10KB
MultirotorRpcLibClient.cpp 9KB
MultirotorRpcLibServer.cpp 7KB
main.cpp 6KB
main.cpp 5KB
FileSystem.cpp 4KB
main.cpp 4KB
ObstacleMap.cpp 4KB
CarRpcLibClient.cpp 2KB
CarRpcLibServer.cpp 2KB
main.cpp 700B
DataCollectorSGM.exe 314KB
AirLib.vcxproj.filters 21KB
UnrealPluginFiles.vcxproj.filters 9KB
Examples.vcxproj.filters 3KB
AirLibUnitTests.vcxproj.filters 2KB
DroneShell.vcxproj.filters 1KB
DroneServer.vcxproj.filters 935B
HelloDrone.vcxproj.filters 935B
AirSimDroneManual.gif 9.21MB
AirSimCarManual.gif 4.85MB
.gitignore 6KB
.gitignore 2KB
.gitignore 322B
.gitignore 98B
.gitignore 43B
.gitignore 5B
.gitmodules 0B
DataCollectorSGM.h 14KB
ctpl_stl.h 10KB
writePNG.h 6KB
RandomPointPoseGeneratorNoRoll.h 1KB
json.hpp 437KB
bitmap_image.hpp 243KB
linenoise.hpp 85KB
AirSimSettings.hpp 56KB
MavLinkMultirotorApi.hpp 47KB
optional.hpp 28KB
FastPhysicsEngine.hpp 22KB
Utils.hpp 21KB
VectorMath.hpp 21KB
SimpleShell.hpp 20KB
AdaptiveController.hpp 18KB
EarthUtils.hpp 18KB
prettyprint.hpp 16KB
DepthNav.hpp 15KB
RpcLibAdapatorsBase.hpp 15KB
MultirotorApiBase.hpp 12KB
SimpleFlightApi.hpp 12KB
StandAloneSensors.hpp 11KB
Px4MultiRotorParams.hpp 10KB
MultiRotorParams.hpp 10KB
MultiRotor.hpp 10KB
DepthNavOptAStar.hpp 10KB
CommonStructs.hpp 10KB
RemoteControl.hpp 9KB
PhysicsBody.hpp 9KB
CommonStructs.hpp 9KB
OffboardApi.hpp 9KB
StereoImageGenerator.hpp 9KB
GeodeticConverter.hpp 8KB
WorkerThread.hpp 7KB
FileSystem.hpp 7KB
EarthCelestial.hpp 7KB
ArduCopterSoloApi.hpp 6KB
Settings.hpp 6KB
Battery.hpp 6KB
DepthNavCost.hpp 6KB
DepthNavThreshold.hpp 6KB
DebugPhysicsBody.hpp 6KB
RpcLibClientBase.hpp 5KB
ScheduledExecutor.hpp 5KB
VehicleApiBase.hpp 5KB
VelocityController.hpp 5KB
Rotor.hpp 5KB
SafetyEval.hpp 5KB
SimpleFlightQuadXParams.hpp 5KB
CarApiBase.hpp 5KB
CascadeController.hpp 5KB
StrictMode.hpp 4KB
ColorUtils.hpp 4KB
共 646 条
- 1
- 2
- 3
- 4
- 5
- 6
- 7
资源评论
JJJ69
- 粉丝: 6365
- 资源: 5917
下载权益
C知道特权
VIP文章
课程特权
开通VIP
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 人物检测26-YOLO(v5至v11)、COCO、CreateML、Paligemma、TFRecord、VOC数据集合集.rar
- 人和箱子检测2-YOLO(v5至v11)、COCO、CreateML、Paligemma、TFRecord、VOC数据集合集.rar
- 清华大学2022年秋季学期 高等数值分析课程报告
- GEE错误集-Cannot add an object of type <Element> to the map. Might be fixable with an explicit .pdf
- 清华大学2022年秋季学期 高等数值分析课程报告
- 矩阵与线程的对应关系图
- 人体人员检测46-YOLO(v5至v9)、COCO、Darknet、TFRecord数据集合集.rar
- GEMM优化代码实现1
- java实现的堆排序 含代码说明和示例.docx
- 资料阅读器(先下载解压) 5.0.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功