Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control

TL;DR

This paper introduces a heterogeneous GNN-based multi-agent reinforcement learning framework for coordinated platooning and traffic signal control to reduce urban congestion, demonstrating improved traffic flow and efficiency in simulations.

Contribution

It presents a novel multi-agent reinforcement learning approach that models signal control and platooning as distinct yet coordinated agents using graph neural networks.

Findings

Converges to optimal traffic flow in SUMO simulations

Reduces travel time and fuel consumption

Outperforms existing adaptive control methods

Abstract

Over the years, reinforcement learning has emerged as a popular approach to develop signal control and vehicle platooning strategies either independently or in a hierarchical way. However, jointly controlling both in real-time to alleviate traffic congestion presents new challenges, such as the inherent physical and behavioral heterogeneity between signal control and platooning, as well as coordination between them. This paper proposes an innovative solution to tackle these challenges based on heterogeneous graph multi-agent reinforcement learning and traffic theories. Our approach involves: 1) designing platoon and signal control as distinct reinforcement learning agents with their own set of observations, actions, and reward functions to optimize traffic flow; 2) designing coordination by incorporating graph neural networks within multi-agent reinforcement learning to facilitate seamless information exchange among agents on a regional scale; 3) applying alternating optimization for training, allowing agents to update their own policies and adapt to other agents' policies. We evaluate our approach through SUMO simulations, which show convergent results in terms of both travel time and fuel consumption, and superior performance compared to other adaptive signal control methods.