Learning MPC for Interaction-Aware Autonomous Driving: A Game-Theoretic Approach

TL;DR

This paper introduces a game-theoretic approach to interaction-aware motion planning for autonomous vehicles, utilizing online learning of other road users' preferences to improve safety and efficiency in traffic scenarios.

Contribution

It presents a novel generalized potential game model combined with an online learning scheme for preferences and constraints of other road users in autonomous driving.

Findings

Effective in highway merging simulations

Improves safety by modeling interactions accurately

Online learning enhances decision-making in dynamic environments

Abstract

We consider the problem of interaction-aware motion planning for automated vehicles in general traffic situations. We model the interaction between the controlled vehicle and surrounding road users using a generalized potential game, in which each road user is assumed to minimize a common cost function subject to shared (collision avoidance) constraints. We propose a quadratic penalty method to deal with the shared constraints and solve the resulting optimal control problem online using an Augmented Lagrangian method based on PANOC. Secondly, we present a simple methodology for learning preferences and constraints of other road users online, based on observed behavior. Through extensive simulations in a highway merging scenario, we demonstrate the practical efficacy of the overall approach as well as the benefits of the proposed online learning scheme.