A modular software stack for scaled autonomous head-to-head racing on 1/10th-scale vehicles, built on commercial off-the-shelf hardware. Used by ForzaETH and the D-ITET Center for Project Based Learning (PBL) at ETH Zurich.

Accompanying this repository, a paper titled ForzaETH Race Stack - Scaled Autonomous Head-to-Head Racing on Fully Commercial off-the-Shelf Hardware is available on Journal of Field Robotics, detailing the system's architecture, algorithms, and performance benchmarks.

NOTE: For extensions on said paper, tied to specific publications, please refer to the later paragraph Additional Publications

NOTE: We have a ROS2 version of this stack, check out the other branches of this repo!

• Installation
• Quick Start
• Getting started
• Contributing
• Acknowledgement
• Citing ForzaETH Race Stack
• Additional Publications

We provide an installation guide here.

To launch a quick end-to-end simulation and run time trials:

# Start the simulator with the base system
roslaunch stack_master base_system.launch map_name:=<map> racecar_version:=NUC2 sim:=True

# Run time trials with the default controller
roslaunch stack_master time_trials.launch

After installation, the car (or the simulation environment) is ready to be tested. For examples on how to run the different modules on the car, refer to the stack_master README. As a further example, the time-trials or the head-to-head checklists are a good starting point.

Or check out our video playlist on Youtube:

Note: Click on the thumbnails to watch the videos.

In case you find our package helpful and want to contribute, please either raise an issue or directly make a pull request. To create pull request please follow the guidelines in CONTRIBUTING.

This project would not be possible without the use of multiple great open-sourced code bases as listed below:

• f1tenth_system
• F1TENTH Racecar Simulator
• Veddar VESC Interface
• Cartographer
• Cartographer ROS Integration
• global_racetrajectory_optimization
• RangeLibc
• BayesOpt4ROS
• cpu_monitor

If you found our race stack helpful in your research, we would appreciate if you cite it as follows:

@article{baumann2024forzaeth,
  title={ForzaETH Race Stack—Scaled Autonomous Head-to-Head Racing on Fully Commercial Off-the-Shelf Hardware},
  author={Baumann, Nicolas and Ghignone, Edoardo and K{\"u}hne, Jonas and Bastuck, Niklas and Becker, Jonathan and Imholz, Nadine and Kr{\"a}nzlin, Tobias and Lim, Tian Yi and L{\"o}tscher, Michael and Schwarzenbach, Luca and others},
  journal={Journal of Field Robotics},
  year={2024},
  publisher={Wiley Online Library}
}

Please refer to the system_identification README.

Please refer to the predictive-spliner README.

This project is licensed under the MIT License. See the LICENSE file for details.