Multi-Vehicle Control in Roundabouts using Decentralized Game-Theoretic Planning

TL;DR

This paper introduces a decentralized game-theoretic planning method for multi-vehicle navigation in roundabouts, reducing computational complexity and improving safety and efficiency in urban driving scenarios.

Contribution

It proposes a decentralized approach that limits game interactions to local neighborhoods, enabling real-time, collision-free multi-vehicle planning in dense urban environments.

Findings

Achieves collision-free, efficient driving in urban roundabouts.

Reduces computation time compared to centralized planning.

Outperforms adapted Intelligent Driver Model in experiments.

Abstract

Safe navigation in dense, urban driving environments remains an open problem and an active area of research. Unlike typical predict-then-plan approaches, game-theoretic planning considers how one vehicle's plan will affect the actions of another. Recent work has demonstrated significant improvements in the time required to find local Nash equilibria in general-sum games with nonlinear objectives and constraints. When applied trivially to driving, these works assume all vehicles in a scene play a game together, which can result in intractable computation times for dense traffic. We formulate a decentralized approach to game-theoretic planning by assuming that agents only play games within their observational vicinity, which we believe to be a more reasonable assumption for human driving. Games are played in parallel for all strongly connected components of an interaction graph, significantly reducing the number of players and constraints in each game, and therefore the time required for planning. We demonstrate that our approach can achieve collision-free, efficient driving in urban environments by comparing performance against an adaptation of the Intelligent Driver Model and centralized game-theoretic planning when navigating roundabouts in the INTERACTION dataset. Our implementation is available at http://github.com/sisl/DecNashPlanning.