Autonomous Racing Software Stack and Simulation Enviroment

This repository contains software for 1/10th scale autonomous race cars to compete in the F1/10 competition. It is developed by the Autonomous Racing Project Group of TU Dortmund.

Documentation

• For general information and documentation check out our wiki page.
• For source code documentation check out the auto-generated Doxygen documentation.

Video of final results and testing

Simulation

Features

We provide several LIDAR based driving algorithms:

• Fast and efficient wallfollowing based on fitting circles into the LIDAR scan
• Sensorfusion of ZED camera and LIDAR data
• Boxing of sensor data
• Voxel based obstacle detection (experimental)
• Heavy workload code is in C++
• Full telemetry logging and HUD display
• Report creation of telemetry data
• ROS navigation stack based implementation that uses SLAM, a precalculated map and path planning
• Deep Reinforcement Learning (Q-Learning and Policy Gradient)
• Neural Networks with evolutionary training
• Depth camera support
• Video recording
• Huge set of display options in RViz
• Management script

Our software works on physical hardware and in a simulated environment using Gazebo. Further features are:

• Automatic emergency braking
• Dead Man's Switch
• Teleoperation via keyboard, Xbox and Playstation controller
• Speedometer and Lap Timer

We also added some more stuff not directly connected to the software, please check out the wiki for more information.

Hardware

Our car is based on a 1/10th scale RC car (Traxxas Ford Fiesta) with these additions:

• CPU/GPU board (NVIDIA Jetson)
• motor controller (FOCBOX)
• LIDAR scanner (Hokuyo UST-10LX)
• an inertial measurement unit (Invensense MPU-9250)
• Brushless DC motor (replaces the standard brushed motor)
• Stereo camera (ZED)

License

This project (excluding git submodules) is under MIT and GPLv3 dual licensed - see the MIT.LICENSE and GPLv3.LICENSE file for details.