Roadside Units Assisted Localized Automated Vehicle Maneuvering: An Offline Reinforcement Learning Approach

TL;DR

This paper introduces an RSU-assisted offline reinforcement learning system for automated vehicle maneuvering at intersections, significantly improving travel efficiency while maintaining safety.

Contribution

It presents a novel cooperative maneuvering system using RSUs and offline RL trained on human data, advancing urban traffic management.

Findings

Travel efficiency increased by up to 17.38% at intersections.

Performance comparable to state-of-the-art autonomous systems in safety.

Effective use of offline RL with twin delayed deep deterministic policy gradient and behavior cloning.

Abstract

Traffic intersections present significant challenges for the safe and efficient maneuvering of connected and automated vehicles (CAVs). This research proposes an innovative roadside unit (RSU)-assisted cooperative maneuvering system aimed at enhancing road safety and traveling efficiency at intersections for CAVs. We utilize RSUs for real-time traffic data acquisition and train an offline reinforcement learning (RL) algorithm based on human driving data. Evaluation results obtained from hardware-in-loop autonomous driving simulations show that our approach employing the twin delayed deep deterministic policy gradient and behavior cloning (TD3+BC), achieves performance comparable to state-of-the-art autonomous driving systems in terms of safety measures while significantly enhancing travel efficiency by up to 17.38% in intersection areas. This paper makes a pivotal contribution to the field of intelligent transportation systems, presenting a breakthrough solution for improving urban traffic flow and safety at intersections.