RAPID: Autonomous Multi-Agent Racing using Constrained Potential Dynamic Games

TL;DR

This paper introduces RAPID, a real-time algorithm for autonomous multi-agent racing based on constrained potential dynamic games, simplifying complex interactions into a single optimal control problem.

Contribution

The paper models multi-agent racing as a constrained dynamic potential game and develops RAPID, an efficient algorithm that enables real-time autonomous racing with improved performance.

Findings

RAPID outperforms state-of-the-art racing algorithms in simulations.

The algorithm demonstrates real-time capabilities in hardware experiments.

Modeling interactions as potential games simplifies the solution process.

Abstract

In this work, we consider the problem of autonomous racing with multiple agents where agents must interact closely and influence each other to compete. We model interactions among agents through a game-theoretical framework and propose an efficient algorithm for tractably solving the resulting game in real time. More specifically, we capture interactions among multiple agents through a constrained dynamic game. We show that the resulting dynamic game is an instance of a simple-to-analyze class of games. Namely, we show that our racing game is an instance of a constrained dynamic potential game. An important and appealing property of dynamic potential games is that a generalized Nash equilibrium of the underlying game can be computed by solving a single constrained optimal control problem instead of multiple coupled constrained optimal control problems. Leveraging this property, we show that the problem of autonomous racing is greatly simplified and develop RAPID (autonomous multi-agent RAcing using constrained PotentIal Dynamic games), a racing algorithm that can be solved tractably in real-time. Through simulation studies, we demonstrate that our algorithm outperforms the state-of-the-art approach. We further show the real-time capabilities of our algorithm in hardware experiments.