Multiagent Reinforcement Learning for Active Guidance Control of Railway Vehicles with Independently Rotating Wheels

被引:2
作者
Wei, Juyao [1 ]
Lu, Zhenggang [1 ]
Yin, Zheng [1 ]
Jing, Zhipeng [1 ]
机构
[1] Tongji Univ, Inst Rail Transit, Shanghai 201804, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 04期
关键词
active guidance control; independently rotating wheels (IRW); prioritized experience replay (PER); multiagent deep deterministic policy gradient (MADDPG); BOGIE;
D O I
10.3390/app14041677
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
This paper presents a novel data-driven multiagent reinforcement learning (MARL) controller for enhancing the running stability of independently rotating wheels (IRW) and reducing wheel-rail wear. We base our active guidance controller on the multiagent deep deterministic policy gradient (MADDPG) algorithm. In this framework, each IRW controller is treated as an independent agent, facilitating localized control of individual wheelsets and reducing the complexity of the required observations. Furthermore, we enhance the MADDPG algorithm with prioritized experience replay (PER), resulting in the PER-MADDPG algorithm, which optimizes training convergence and stability by prioritizing informative experience samples. In this paper, we compare the PER-MADDPG algorithm against existing controllers, demonstrating the superior simulation performance of the proposed algorithm, particularly in terms of self-centering capability and curve-negotiation behavior, effectively reducing the wear number. We also develop a scaled IRW vehicle for active guidance experiments. The experimental results validate the enhanced running performance of IRW vehicles using our proposed controller.
引用
收藏
页数:21
相关论文
共 31 条
[1]   Control of the Lateral Displacement Restoring Force of IRWs for Sharp Curved Driving [J].
Ahn, Hanwoong ;
Lee, Hyungwoo ;
Go, Sungchul ;
Cho, Yonho ;
Lee, Ju .
JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, 2016, 11 (04) :1042-1048
[2]   Robust Multi-Agent Reinforcement Learning Method Based on Adversarial Domain Randomization for Real-World Dual-UAV Cooperation [J].
Chen, Shutong ;
Liu, Guanjun ;
Zhou, Ziyuan ;
Zhang, Kaiwen ;
Wang, Jiacun .
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2024, 9 (01) :1615-1627
[3]   Autonomous driving planning and decision making based on game theory and reinforcement learning [J].
Duan, Weiping ;
Tang, Zhongyi ;
Liu, Wei ;
Zhou, Hongbiao .
EXPERT SYSTEMS, 2023, 40 (05)
[4]   Active suspension in railway vehicles: a literature survey [J].
Fu, Bin ;
Giossi, Rocco Libero ;
Persson, Rickard ;
Stichel, Sebastian ;
Bruni, Stefano ;
Goodall, Roger .
RAILWAY ENGINEERING SCIENCE, 2020, 28 (01) :3-35
[5]  
Grether Gustav, 2017, Proceedings in Applied Mathematics and Mechanics, V17, P797, DOI 10.1002/pamm.201710366
[6]   Active Guidance of a Railway Running Gear with Independently Rotating Wheels [J].
Heckmann, Andreas ;
Keck, Alexander ;
Grether, Gustav .
2020 IEEE VEHICLE POWER AND PROPULSION CONFERENCE (VPPC), 2020,
[7]   A survey and critique of multiagent deep reinforcement learning [J].
Hernandez-Leal, Pablo ;
Kartal, Bilal ;
Taylor, Matthew E. .
AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2019, 33 (06) :750-797
[8]   Steering Performance Evaluation of Active Steering Bogie to Reduce Wheel Wear on Test Line [J].
Hur, Hyunmoo ;
Shin, Yujeong ;
Ahn, Dahoon ;
Ham, Youngsam .
INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING, 2019, 20 (09) :1591-1600
[9]  
Iwnicki S., 2019, Handbook of Railway Vehicle Dynamics, V2nd ed., P826
[10]   Boundary conditions of active steering control of independent rotating wheelset based on hub motor and wheel rotating speed difference feedback [J].
Ji, Yuanjin ;
Ren, Lihui ;
Zhou, Jinsong .
VEHICLE SYSTEM DYNAMICS, 2018, 56 (12) :1883-1898