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

2024-05-06

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC)

AI Summary

To address real-time congestion mitigation at highway bottlenecks under mixed traffic, this paper proposes a cooperative optimization method leveraging longitudinal control of human-driven vehicles by autonomous vehicles (AVs). Methodologically, we formulate a decentralized partially observable Markov decision process (Dec-POMDP) framework and design an enhanced multi-agent Rollout algorithm that supports dynamic agent counts and per-agent policy iteration, enabling implicit coordination. Our key contribution is the first integration of the Rollout mechanism into Dec-POMDP to jointly ensure real-time responsiveness and cooperative performance—specifically tailored for low AV penetration rates (10%). In large-scale realistic network simulations, the approach reduces average bottleneck travel time by 9.42%, demonstrating its effectiveness and practicality in dynamic, partially observable, and heterogeneous traffic environments.

Technology Category

• Search and Optimization: Learning to Search
• Multiagent Systems: Coordination and Collaboration
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: The sharing economy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Optimizing traffic flow in mixed autonomy highways
• Coordinating AVs to reduce bottleneck congestion
• Decentralized control for dynamic agent scenarios

Innovation

• Multi-agent rollout algorithm for traffic optimization
• Decentralized Dec-POMDP modeling for mixed autonomy
• Agent-by-agent policy iterations for dynamic adaptation