Partial End-to-end Reinforcement Learning for Robustness Against Modelling Error in Autonomous Racing
This addresses robustness issues in autonomous racing for practical applications, but it is incremental as it builds on existing RL and classical control techniques.
The paper tackles the problem of improving reinforcement learning for autonomous racing under vehicle modeling errors by proposing a partial end-to-end algorithm that decouples planning and control, resulting in better robustness compared to standard end-to-end methods.
In this paper, we address the issue of increasing the performance of reinforcement learning (RL) solutions for autonomous racing cars when navigating under conditions where practical vehicle modelling errors (commonly known as \emph{model mismatches}) are present. To address this challenge, we propose a partial end-to-end algorithm that decouples the planning and control tasks. Within this framework, an RL agent generates a trajectory comprising a path and velocity, which is subsequently tracked using a pure pursuit steering controller and a proportional velocity controller, respectively. In contrast, many current learning-based (i.e., reinforcement and imitation learning) algorithms utilise an end-to-end approach whereby a deep neural network directly maps from sensor data to control commands. By leveraging the robustness of a classical controller, our partial end-to-end driving algorithm exhibits better robustness towards model mismatches than standard end-to-end algorithms.