Incorporating Recurrent Reinforcement Learning into Model Predictive Control for Adaptive Control in Autonomous Driving
This addresses adaptive control for autonomous vehicles, but it is incremental as it combines existing techniques (MPC and RRL) for a specific domain.
The paper tackled the problem of Model Predictive Control (MPC) in autonomous driving failing to adapt to real-world perturbations due to static parameters, by incorporating Recurrent Reinforcement Learning (RRL) to adaptively update the dynamics model parameters, resulting in robust behaviors evaluated in the CARLA simulator.
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.