A Game-Theoretic Approach to Decision Making for Multiple Vehicles at Roundabout

TL;DR

This paper introduces a game-theoretic decision-making framework for autonomous vehicles at roundabouts, balancing safety and efficiency by modeling interactions as a finite sequential game and predicting behaviors via Nash equilibrium.

Contribution

It presents a novel distributed decision-making process that estimates vehicle aggressiveness and uses game theory to improve safety and traffic flow at roundabouts.

Findings

The approach reduces collision risk in simulations.

It improves traffic throughput and reduces delay.

The method effectively predicts vehicle behaviors.

Abstract

In this paper, we study the decision making of multiple autonomous vehicles at a roundabout. The behaviours of the vehicles depend on their aggressiveness, which indicates how much they value speed over safety. We propose a distributed decision-making process that balances safety and speed of the vehicles. In the proposed process, each vehicle estimates other vehicles' aggressiveness and formulates the interactions among the vehicles as a finite sequential game. Based on the Nash equilibrium of this game, the vehicle predicts other vehicles' behaviours and makes decisions. We perform numerical simulations to illustrate the effectiveness of the proposed process, both for safety (absence of collisions), and speed (time spent within the roundabout).