This paper explores the use of reinforcement learning (RL) in the context of autonomous vehicle racing, specifically focusing on the F1TENTH simulation platform. While commercial autonomous driving often employs classic control algorithms, the state-of-the-art solutions, including those in the F1TENTH domain, increasingly rely on RL. Notably, RL-based approaches have shown superhuman performance in simulated environments, as seen in drone racing and the recent achievement by Sony in autonomous racing. In this paper we propose a novel LiDAR-only observation for learning vehicle dynamics, and test it with a widely accessible model-free RL method. The trained agent demonstrates the capability to transfer its driving skills to previously unseen tracks. Additionally, the paper provides recommendations for selecting hyperparameters, contributing valuable insights for newcomers to the field of autonomous racing.

The advancement of AI technologies and the increasing processing power of computers have made high-speed autonomous racing possible. Different leagues, such as the Abu Dhabi Autonomous Racing League (A2RL) and the Indy Autonomous Challenge (IAC), are organizing races in simulation and with real race cars. In this paper we will describe our experience with the inaugural A2RL event and a SIM race organized by IAC. With respect to A2RL, we will give an overview of the physical parameters of the race car, the sensors we worked with, and our software solution including how we created trajectories for different test scenarios.