自动驾驶汽车近年来非常热门，也是本书第10章的内容，优酷小站也分享过很多这方面主题的视频。

可以参考的一些内容如：

1 RC小车：http://blog.csdn.net/ZhangRelay/article/details/71749723

2 自动驾驶汽车仿真：http://blog.csdn.net/ZhangRelay/article/details/74534069

3 从零开始学习无人驾驶技术：https://www.leiphone.com/news/201706/RuoKaDSTmd1dClUV.html

4 comma.ai：https://comma.ai/

5 openpilot：https://github.com/commaai/openpilot

6 apollo.auto：http://apollo.auto/index_cn.html

7 apolloauto：https://github.com/apolloauto

仿真平台：https://github.com/udacity/self-driving-car-sim

Welcome to Udacity's Self-Driving Car Simulator

This simulator was built for Udacity's Self-Driving Car Nanodegree, to teach students how to train cars how to navigate road courses using deep learning. See more project details here.

All the assets in this repository require Unity. Please follow the instructions below for the full setup.

Avaliable Game Builds (Precompiled builds of the simulator)

Instructions: Download the zip file, extract it and run the exectution file.

Version 2, 2/07/17

LinuxMacWindows

Version 1, 12/09/16

LinuxMacWindows 32Windows 64

Unity Simulator User Instructions

1. Clone the repository to your local directory, please make sure to use Git LFS to properly pull over large texture and model assets.

2. Install the free game making engine Unity, if you dont already have it. Unity is necessary to load all the assets.

3. Load Unity, Pick load exiting project and choice the self-driving-car-sim folder.

4. Load up scenes by going to Project tab in the bottom left, and navigating to the folder Assets/1_SelfDrivingCar/Scenes. To load up one of the scenes, for example the Lake Track, double click the file LakeTrackTraining.unity. Once the scene is loaded up you can fly around it in the scene viewing window by holding mouse right click to turn, and mouse scroll to zoom.

5. Play a scene. Jump into game mode anytime by simply clicking the top play button arrow right above the viewing window.

6. View Scripts. Scripts are what make all the different mechanics of the simulator work and they are located in two different directories, the first is Assets/1_SelfDrivingCar/Scripts which mostly relate to the UI and socket connections. The second directory for scripts is Assets/Standard Assets/Vehicle/Car/Scripts and they control all the different interactions with the car.

7. Building a new track. You can easily build a new track by using the prebuilt road prefabs located in Assets/RoadKit/Prefabs click and drag the road prefab pieces onto the editor, you can snap road pieces together easily by using vertex snapping by holding down "v" and dragging a road piece close to another piece.

最火爆的源码可以参考：https://github.com/CPFL/Autoware

Open-source software for urban self-driving mobility

Autoware

Open-source software for urban autonomous driving, maintained by Tier IV. The following functions are supported:

• 3D Localization
• 3D Mapping
• Path Planning
• Path Following
• Accel/Brake/Steering Control
• Data Logging
• Car/Pedestrian/Object Detection
• Traffic Signal Detection
• Traffic Light Recognition
• Lane Detection
• Object Tracking
• Sensor Calibration
• Sensor Fusion
• Cloud-oriented Maps
• Connected Automation
• Smartphone Navigation
• Software Simulation
• Virtual Reality

Autoware is protected by the BSD License. Please use it on at your own discretion. For safe use, we provide a ROSBAG-based simulation method for those who do not own real autonomous vehicles. In case you use Autoware with real autonomous vehicles, please formulate safety measures and assessment of risk before field testing.

Manuals and Documents

Free manuals can be found at https://github.com/CPFL/Autoware-Manuals. You are encouraged to join maintenance of those manuals. Thanks for your cooperation!

See also branching_model for the tips of Autoware development, including the coding style and branching model.

License

• New BSD License
  • See LICENSE

Spec Recommendation

• Number of CPU cores: 8
• RAM size: 32GB
• Storage size: 30GB

Requirements

• ROS indigo (Ubuntu 14.04) or ROS jade (Ubuntu 15.04) or ROS kinetic (Ubuntu 16.04)
• OpenCV 2.4.10 or higher
• Qt 5.2.1 or higher
• CUDA(Optional)
• FlyCapture2 (Optional)
• Armadillo (Optional)

Please use checkout revision before 2015/OCT/21 if you use Autoware on ROS hydro or Ubuntu 13.04, 13.10.

Install dependencies for Ubuntu 14.04 indigo

  

   

    

     

    
    

     

      % sudo apt-get install ros-indigo-desktop-full ros-indigo-nmea-msgs ros-indigo-nmea-navsat-driver ros-indigo-sound-play ros-indigo-jsk-visualization ros-indigo-grid-map ros-indigo-gps-common
     
    
   

    

     

    
    

     

      % sudo apt-get install ros-indigo-controller-manager ros-indigo-ros-control ros-indigo-ros-controllers ros-indigo-gazebo-ros-control ros-indigo-sicktoolbox ros-indigo-sicktoolbox-wrapper ros-indigo-joystick-drivers ros-indigo-novatel-span-driver
     
    
   

    

     

    
    

     

      % sudo apt-get install libnlopt-dev freeglut3-dev qtbase5-dev libqt5opengl5-dev libssh2-1-dev libarmadillo-dev libpcap-dev gksu libgl1-mesa-dev libglew-dev
     
    
  
 

NOTE: Please do not install ros-indigo-velodyne-pointcloud package. Please uninstall it if you already installed.

Install dependencies for Ubuntu 16.04 kinetic

  

   

    

     

    
    

     

      % sudo apt-get install ros-kinetic-desktop-full ros-kinetic-nmea-msgs ros-kinetic-nmea-navsat-driver ros-kinetic-sound-play ros-kinetic-jsk-visualization ros-kinetic-grid-map ros-kinetic-gps-common
     
    
   

    

     

    
    

     

      % sudo apt-get install ros-kinetic-controller-manager ros-kinetic-ros-control ros-kinetic-ros-controllers ros-kinetic-gazebo-ros-control ros-kinetic-joystick-drivers
     
    
   

    

     

    
    

     

      % sudo apt-get install libnlopt-dev freeglut3-dev qtbase5-dev libqt5opengl5-dev libssh2-1-dev libarmadillo-dev libpcap-dev gksu libgl1-mesa-dev libglew-dev python-wxgtk3.0
     
    
  
 

NOTE: Following packages are not supported in ROS Kinetic.

• gazebo
• orb slam
• dpm ocv

How to Build

  

   

    

     

    
    

     

      $ cd $HOME
     
    
   

    

     

    
    

     

      $ git clone https://github.com/CPFL/Autoware.git
     
    
   

    

     

    
    

     

      $ cd ~/Autoware/ros/src
     
    
   

    

     

    
    

     

      $ catkin_init_workspace
     
    
   

    

     

    
    

     

      $ cd ../
     
    
   

    

     

    
    

     

      $ ./catkin_make_release
     
    
  
 

###Caffe based object detectorsCV based detectors RCNN and SSD nodes are not automatically built.

To build these nodes please follow the respective node's READMESSDRCNNYolo2

How to Start

  

   

    

     

    
    

     

      $ cd $HOME/Autoware/ros
     
    
   

    

     

    
    

     

      $ ./run
     
    
  
 

For Developers

Be careful when changing files under ros/src/sensing/drivers/lidar/packages/velodyne. There is subtree.The original repository is here. If you change those files from thisrepository, you must use git subtree push. (Please never change and push code if you don't understandgit subtree well).

GitFlow, the git branching model, is used in the Autoware repository.

• When you adding new features, you can branch off your feature branch from develop.
  you can use the following command.
  $ git checkout -b feature/[your_branch_name] develop
• When you find bugs in master, you can branch off your hotfix branch from master.
  you can use the following command.
  $ git checkout -b hotfix/[your_branch_name] master

See docs/en/branching_model.md

More details here

Main Packages

Localization

• ndt_localizer
• icp_localizer

Detection

• lidar_tracker
• cv_tracker
• road_wizard

Mission (Global) Planning

• lane_planner
• way_planner
• freespace_planner

Motion (Local) Planning

• astar_planner
• lattice_planner
• dp_planner

Vehicle Control

• waypoint_follower
• waypoint_maker

Research Papers for Citation

1. S. Kato, E. Takeuchi, Y. Ishiguro, Y. Ninomiya, K. Takeda, and T. Hamada. "An Open Approach to Autonomous Vehicles", IEEE Micro, Vol. 35, No. 6, pp. 60-69, 2015.

Demo Videos

Public Road Demonstration

Test Field Demonstration

Instruction Videos

Quick Start

Loading Map Data

Localization with GNSS

Localization without GNSS

Mapping

Detection with SSD

Detection with Yolo2

Detection with DPM

Detection with Euclidean Clustering

Traffic Light Recognition

Planning with ROSBAG

Planning with wf_simulator

Planning with Hybrid State A*

Calibration Toolkit

Data Processor for Bag File

Ftrace

Sample Data

3D map of Moriyama in Nagoya

ROSBAG data of Moriyama driving

Script for generating demo launch files of Moriyama

ROSBAG data for Calibration

IROS 2016 Data

ROSBAG data of Nagoya driving

Contact

Autoware Developers (autoware@googlegroups.com)

Autoware Developers Slack Team (https://autoware.herokuapp.com/)

To subscribe to the Autoware Developers mailing list,

• If you have a Google account, go to https://groups.google.com/d/forum/autoware, and click the Apply to Join Group button.
• If you don't have a Google account, send an email to autoware+subscribe@googlegroups.com.

文章来源: zhangrelay.blog.csdn.net，作者：zhangrelay，版权归原作者所有，如需转载，请联系作者。

原文链接：zhangrelay.blog.csdn.net/article/details/77324002