A Distributed Approach to Autonomous Intersection Management via Multi-Agent Reinforcement Learning

TL;DR

This paper presents a distributed multi-agent reinforcement learning approach for autonomous intersection management that eliminates the need for centralized control, utilizing advanced vehicle sensors and a novel training strategy.

Contribution

It introduces a MARL-based algorithm for intersection control and a new prioritised scenario replay strategy to enhance training effectiveness.

Findings

Outperforms traditional centralized AIM methods in virtual tests

Demonstrates accurate intersection navigation without central control

Validates approach using SMARTS platform benchmarks

Abstract

Autonomous intersection management (AIM) poses significant challenges due to the intricate nature of real-world traffic scenarios and the need for a highly expensive centralised server in charge of simultaneously controlling all the vehicles. This study addresses such issues by proposing a novel distributed approach to AIM utilizing multi-agent reinforcement learning (MARL). We show that by leveraging the 3D surround view technology for advanced assistance systems, autonomous vehicles can accurately navigate intersection scenarios without needing any centralised controller. The contributions of this paper thus include a MARL-based algorithm for the autonomous management of a 4-way intersection and also the introduction of a new strategy called prioritised scenario replay for improved training efficacy. We validate our approach as an innovative alternative to conventional centralised AIM techniques, ensuring the full reproducibility of our results. Specifically, experiments conducted in virtual environments using the SMARTS platform highlight its superiority over benchmarks across various metrics.