Autonomous Vehicle Lateral Control Using Deep Reinforcement Learning with MPC-PID Demonstration

TL;DR

This paper presents a deep reinforcement learning-based lateral control method for autonomous vehicles that integrates traditional MPC-PID control as a demonstration to improve robustness and training stability, evaluated in simulation.

Contribution

It introduces a novel control approach combining MPC-PID with deep reinforcement learning to enhance autonomous vehicle lateral control under model imperfections.

Findings

Effective control with incomplete vehicle information

Stable DRL training via demonstration

Potential to reduce development efforts

Abstract

The controller is one of the most important modules in the autonomous driving pipeline, ensuring the vehicle reaches its desired position. In this work, a reinforcement learning based lateral control approach, despite the imperfections in the vehicle models due to measurement errors and simplifications, is presented. Our approach ensures comfortable, efficient, and robust control performance considering the interface between controlling and other modules. The controller consists of the conventional Model Predictive Control (MPC)-PID part as the basis and the demonstrator, and the Deep Reinforcement Learning (DRL) part which leverages the online information from the MPC-PID part. The controller's performance is evaluated in CARLA using the ground truth of the waypoints as inputs. Experimental results demonstrate the effectiveness of the controller when vehicle information is incomplete, and the training of DRL can be stabilized with the demonstration part. These findings highlight the potential to reduce development and integration efforts for autonomous driving pipelines in the future.