原文传递
Performance of State-Shared Multiagent Deep Reinforcement Learning Controlled Signal Corridor with Platooning-Based CAVs
| 题名： | Performance of State-Shared Multiagent Deep Reinforcement Learning Controlled Signal Corridor with Platooning-Based CAVs |
| 正文语种： | eng |
| 作者： | Li Song;Wei 'David' Fan |
| 作者单位： | School of Transportation and Logistics Engineering Wuhan Univ. of Technology Wuhan Civil Bldg. Room 404 1178 Heping Blvd. Wuhan 430063 China Dept. of Civil and Environmental Engineering Univ. of North Carolina at Charlotte EPIC Bldg. Room 3366 9201 University City Blvd. Charlotte NC 28223-0001;USDOT Center for Advanced Multimodal Mobility Solutions and Education (CAMMSE) Charlotte NC 28223-0001 Dept. of Civil and Environmental Engineering Univ. of North Carolina at Charlotte EPIC Bldg. Room 3261 9201 University City Blvd. Charlotte NC 28223-0001 |
| 关键词： | Multiagent deep reinforcement learning (MADRL); Traffic signal control; Connected and automated vehicle (CAV); Platooning |
| 摘要： | The emerging technologies of connected and automated vehicles (CAVs) and deep reinforcement learning (DRL) provide innovative methods and have a great potential for developing new solutions to improve the efficiency of several intersection systems. Based on the multisource data collected from the transportation environments, CAVs with the cooperative adaptive cruise control (CACC) system could merge into platoons and traverse the intersection quickly and smoothly. Meanwhile, the traffic information about the CAVs enables intelligent traffic signal controls with the help of DRL technologies. This research investigates the performance of a state-shared multiagent deep reinforcement learning (MADRL) controlled signal corridor with platooning-based CAVs. A corridor with seven intersections from the Ingolstadt Traffic Scenario (InTAS) in Germany is selected as a case study. The state information is shared between neighboring intersections to overcome the partial information observation of the decentralized agents in the MADRL framework. A platooning framework with specific CACC systems for the leading and following vehicles is proposed. Results indicate that the state-shared MADRL with CAV platoons could significantly decrease the total waiting time, average queue length, and total CO_2 emission of the corridor by 80%, 73%, and 54%, respectively, which could be beneficial in further improving the intersection efficiency, designing future intersections, and cooperating signals and CAVs platoons. |
| 出版年： | 2023 |
| 期刊名称： | Journal of Transportation Engineering |
| 卷： | 149 |
| 期： | 8 |
| 页码： | 04023072.1-04023072.10 |
相关文献
- An Attention Reinforcement Learning-Based Strategy for Large-Scale Adaptive Traffic Signal Control System
- Online longitudinal trajectory planning for connected and autonomous vehicles in mixed traffic flow with deep reinforcement learning approach
- Multiagent Soft Actor-Critic for Traffic Light Timing
- Network-wide traffic signal control based on the discovery of critical nodes and deep reinforcement learning
- A cold-start-free reinforcement learning approach for traffic signal control
- Signalized Intersection Performance with Automated and Conventional Vehicles: A Comparative Study
检索历史
应用推荐
