A Multi-Agent Rollout Approach for Highway Bottleneck Decongestion in Mixed Autonomy

TL;DR

This paper presents a multi-agent rollout method for coordinating autonomous and human-driven vehicles to reduce highway congestion, demonstrating significant improvements in traffic flow and travel time reduction in real-world simulations.

Contribution

It introduces a novel decentralized multi-agent rollout algorithm for traffic optimization in mixed autonomy environments, effectively coordinating AVs and human drivers in dynamic scenarios.

Findings

Reduces average travel time by 9.42% at 10% AV penetration

Effectively adapts to varying numbers of agents and traffic conditions

Improves traffic flow at highway bottlenecks through decentralized control

Abstract

The integration of autonomous vehicles (AVs) into the existing transportation infrastructure offers a promising solution to alleviate congestion and enhance mobility. This research explores a novel approach to traffic optimization by employing a multi-agent rollout approach within a mixed autonomy environment. The study concentrates on coordinating the speed of human-driven vehicles by longitudinally controlling AVs, aiming to dynamically optimize traffic flow and alleviate congestion at highway bottlenecks in real-time. We model the problem as a decentralized partially observable Markov decision process (Dec-POMDP) and propose an improved multi-agent rollout algorithm. By employing agent-by-agent policy iterations, our approach implicitly considers cooperation among multiple agents and seamlessly adapts to complex scenarios where the number of agents dynamically varies. Validated in a real-world network with varying AV penetration rates and traffic flow, the simulations demonstrate that the multi-agent rollout algorithm significantly enhances performance, reducing average travel time on bottleneck segments by 9.42% with a 10% AV penetration rate.