Incorporating Recurrent Reinforcement Learning into Model Predictive Control for Adaptive Control in Autonomous Driving

TL;DR

This paper introduces a novel adaptive control method for autonomous driving that combines Model Predictive Control with Recurrent Reinforcement Learning to improve robustness against uncertainties and perturbations.

Contribution

It reformulates MPC as a POMDP and integrates RRL for continual adaptation of the dynamics model, enhancing robustness in autonomous driving.

Findings

MPC-RRL achieves robust behavior under various perturbations.

The approach effectively adapts to internal and external uncertainties.

Simulation results demonstrate improved control performance.

Abstract

Model Predictive Control (MPC) is attracting tremendous attention in the autonomous driving task as a powerful control technique. The success of an MPC controller strongly depends on an accurate internal dynamics model. However, the static parameters, usually learned by system identification, often fail to adapt to both internal and external perturbations in real-world scenarios. In this paper, we firstly (1) reformulate the problem as a Partially Observed Markov Decision Process (POMDP) that absorbs the uncertainties into observations and maintains Markov property into hidden states; and (2) learn a recurrent policy continually adapting the parameters of the dynamics model via Recurrent Reinforcement Learning (RRL) for optimal and adaptive control; and (3) finally evaluate the proposed algorithm (referred as $\textit{MPC-RRL}$) in CARLA simulator and leading to robust behaviours under a wide range of perturbations.