F1TENTH: An Open-source Evaluation Environment for Continuous Control and Reinforcement Learning
Matthew O’Kelly, Hongrui Zheng, Dhruv Karthik, Rahul Mangharam · 2019
The deployment and evaluation of learning algorithms on autonomous vehicles (AV) is expensive, slow, and potentially unsafe. This paper details the F1TENTH autonomous racing platform, an open-source evaluation framework for training, testing, and evaluating autonomous systems. With 1/10th-scale low-cost hardware and multiple virtual environments, F1TENTH enables safe and rapid experimentation of AV algorithms even in laboratory research settings. We present three benchmark tasks and baselines in the set- ting of autonomous racing, demonstrating the flexibility and features of our evaluation environment.