This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Constraint-Guided Behavior Transformer for Centralized Coordination of Connected and Automated Vehicles at Intersections
1
College of Automotive Engineering, Jilin University, Changchun 130025, China
2
Graduate School of Information and Science Technology, The University of Tokyo, Tokyo 113-8654, Japan
3
School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China
4
National Key Laboratory of Automotive Chassis Integration and Bionics, Jilin University, Changchun 130025, China
*
Author to whom correspondence should be addressed.
Sensors 2024, 24(16), 5187; https://doi.org/10.3390/s24165187 (registering DOI)
Submission received: 9 July 2024
/
Revised: 6 August 2024
/
Accepted: 9 August 2024
/
Published: 11 August 2024
Abstract
The centralized coordination of Connected and Automated Vehicles (CAVs) at unsignalized intersections aims to enhance traffic efficiency, driving safety, and passenger comfort. Autonomous Intersection Management (AIM) systems introduce a novel approach for centralized coordination. However, existing rule-based and optimization methods often face the challenges of poor generalization and low computational efficiency when dealing with complex traffic environments and highly dynamic traffic conditions. Additionally, current Reinforcement Learning (RL)-based methods encounter difficulties around policy inference and safety. To address these issues, this study proposes Constraint-Guided Behavior Transformer for Safe Reinforcement Learning (CoBT-SRL), which uses transformers as the policy network to achieve efficient decision-making for vehicle driving behaviors. This method leverages the ability of transformers to capture long-range dependencies and improve data sample efficiency by using historical states, actions, and reward and cost returns to predict future actions. Furthermore, to enhance policy exploration performance, a sequence-level entropy regularizer is introduced to encourage policy exploration while ensuring the safety of policy updates. Simulation results indicate that CoBT-SRL exhibits stable training progress and converges effectively. CoBT-SRL outperforms other RL methods and vehicle intersection coordination schemes (VICS) based on optimal control in terms of traffic efficiency, driving safety, and passenger comfort.
Share and Cite
MDPI and ACS Style
Zhao, R.; Fan, Y.; Li, Y.; Wang, K.; Gao, F.; Gao, Z.
Constraint-Guided Behavior Transformer for Centralized Coordination of Connected and Automated Vehicles at Intersections. Sensors 2024, 24, 5187.
https://doi.org/10.3390/s24165187
AMA Style
Zhao R, Fan Y, Li Y, Wang K, Gao F, Gao Z.
Constraint-Guided Behavior Transformer for Centralized Coordination of Connected and Automated Vehicles at Intersections. Sensors. 2024; 24(16):5187.
https://doi.org/10.3390/s24165187
Chicago/Turabian Style
Zhao, Rui, Yuze Fan, Yun Li, Kui Wang, Fei Gao, and Zhenhai Gao.
2024. "Constraint-Guided Behavior Transformer for Centralized Coordination of Connected and Automated Vehicles at Intersections" Sensors 24, no. 16: 5187.
https://doi.org/10.3390/s24165187
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.