Multi-Agent Deep Reinforcement Learning for Distributed and Autonomous Platoon Coordination via Speed-regulation over Large-scale Transportation Networks

TL;DR

This paper introduces a multi-agent deep reinforcement learning framework for autonomous truck platoon coordination in large-scale networks, optimizing fuel efficiency and traffic flow through decentralized decision-making.

Contribution

The paper proposes TA-QMIX, a novel multi-agent DRL method with attention mechanisms for large-scale, distributed platoon coordination, enabling autonomous and cooperative decision-making.

Findings

Achieves 19.17% fuel savings in large-scale simulations

Decentralized policy operates with decision time of 0.001 seconds

Effective cooperation among trucks improves traffic efficiency

Abstract

Truck platooning technology enables a group of trucks to travel closely together, with which the platoon can save fuel, improve traffic flow efficiency, and improve safety. In this paper, we consider the platoon coordination problem in a large-scale transportation network, to promote cooperation among trucks and optimize the overall efficiency. Involving the regulation of both speed and departure times at hubs, we formulate the coordination problem as a complicated dynamic stochastic integer programming under network and information constraints. To get an autonomous, distributed, and robust platoon coordination policy, we formulate the problem into a model of the Decentralized-Partial Observable Markov Decision Process. Then, we propose a Multi-Agent Deep Reinforcement Learning framework named Trcuk Attention-QMIX (TA-QMIX) to train an efficient online decision policy. TA-QMIX utilizes the attention mechanism to enhance the representation of truck fuel gains and delay times, and provides explicit truck cooperation information during the training process, promoting trucks' willingness to cooperate. The training framework adopts centralized training and distributed execution, thus training a policy for trucks to make decisions online using only nearby information. Hence, the policy can be autonomously executed on a large-scale network. Finally, we perform comparison experiments and ablation experiments in the transportation network of the Yangtze River Delta region in China to verify the effectiveness of the proposed framework. In a repeated comparative experiment with 5,000 trucks, our method average saves 19.17\% of fuel with an average delay of only 9.57 minutes per truck and a decision time of 0.001 seconds.