The development of vehicle controllers for autonomous racing is challenging because racing cars operate at their physical driving limit. Prompted by the demand for improved performance, autonomous racing research has seen the proliferation of machine learning-based controllers. While these approaches show competitive performance, their practical applicability is often limited. Residual policy learning promises to mitigate this by combining classical controllers with learned residual controllers. The critical advantage of residual controllers is their high adaptability parallel to the classical controller's stable behavior. We propose a residual vehicle controller for autonomous racing cars that learns to amend a classical controller for the path-following of racing lines. In an extensive study, performance gains of our approach are evaluated for a simulated car of the F1TENTH autonomous racing series. The evaluation for twelve replicated real-world racetracks shows that the residual controller reduces lap times by an average of 4.55 % compared to a classical controller and zero-shot generalizes to new racetracks.

翻译：自主赛车的车辆控制器开发极具挑战性，因为赛车在物理极限状态下运行。为应对性能提升需求，自主赛车研究中基于机器学习的控制器日益增多。尽管这些方法展现出竞争性能，但其实际应用往往受限。残差策略学习有望通过将经典控制器与学习得到的残差控制器相结合来缓解这一问题。残差控制器的关键优势在于其高适应性，同时保留了经典控制器的稳定特性。我们提出了一种用于自主赛车的残差车辆控制器，该控制器学习改进经典控制器的赛道线路径跟踪能力。通过广泛研究，针对F1TENTH自主赛车系列中的模拟车辆评估了该方法带来的性能提升。在十二个复现真实赛道的评估中，残差控制器相比经典控制器平均缩短了4.55%的单圈时间，并能零样本泛化至新赛道。