Optimal Weight Adaptation of Model Predictive Control for Connected and Automated Vehicles in Mixed Traffic with Bayesian Optimization

TL;DR

This paper introduces a Bayesian optimization-based method to adapt the weights in model predictive control for connected and automated vehicles, improving their interaction with human-driven vehicles in mixed traffic scenarios.

Contribution

It presents a novel approach combining game-theoretic MPC, inverse reinforcement learning, and Bayesian optimization for online weight adaptation in CAVs.

Findings

Optimized weight adaptation reduces crossing time at intersections.

The method improves safety and efficiency in mixed traffic simulations.

Adaptive weights outperform fixed-weight MPC strategies.

Abstract

In this paper, we develop an optimal weight adaptation strategy of model predictive control (MPC) for connected and automated vehicles (CAVs) in mixed traffic. We model the interaction between a CAV and a human-driven vehicle (HDV) as a simultaneous game and formulate a game-theoretic MPC problem to find a Nash equilibrium of the game. In the MPC problem, the weights in the HDV's objective function can be learned online using moving horizon inverse reinforcement learning. Using Bayesian optimization, we propose a strategy to optimally adapt the weights in the CAV's objective function so that the expected true cost when using MPC in simulations can be minimized. We validate the effectiveness of the optimal strategy by numerical simulations of a vehicle crossing example at an unsignalized intersection.