Tuning Path Tracking Controllers for Autonomous Cars Using Reinforcement Learning

TL;DR

This paper introduces a reinforcement learning-based method to adaptively tune path tracking controllers for autonomous vehicles, improving navigation accuracy and safety in diverse driving scenarios within a simulated environment.

Contribution

It presents a novel RL-based tuning approach for vehicle controllers, integrating a four-parameter controller with an educated Q-Learning algorithm in a realistic simulation setup.

Findings

Vehicle adapts to different trajectories with low errors

The RL tuning improves tracking accuracy

System demonstrates safe navigation in simulation

Abstract

This paper proposes an adaptable path tracking control system based on Reinforcement Learning (RL) for autonomous cars. A four-parameter controller shapes the behavior of the vehicle to navigate on lane changes and roundabouts. The tuning of the tracker uses an educated Q-Learning algorithm to minimize the lateral and steering trajectory errors. The CARLA simulation environment was used both for training and testing. The results show the vehicle is able to adapt its behavior to the different types of reference trajectories, navigating safely with low tracking errors. The use of a ROS bridge between the CARLA and the tracker results (i) in a realistic system, and (ii) simplifies the replacement of the CARLA by a real vehicle. An argument on the dependability of the overall architecture based on stability results of non-smooth systems is presented at the end of the paper.