Volume 26 Issue 7
Jul.  2026
Turn off MathJax
Article Contents
Article Navigation >  Journal of Traffic and Transportation Engineering  > 2026  >  26(7): 176-189
Next Previous
LI Jian, LI Shuai, SU Yan-zhao, CHENG Kun, XU Hai-jun, HUANG Jin, CHEN Jun-jie. Reinforcement learning anti-rollover control for distributed electric drive multi-axle emergency rescue vehicles[J]. Journal of Traffic and Transportation Engineering, 2026, 26(7): 176-189. doi: 10.19818/j.cnki.1671-1637.2026.297
Citation: LI Jian, LI Shuai, SU Yan-zhao, CHENG Kun, XU Hai-jun, HUANG Jin, CHEN Jun-jie. Reinforcement learning anti-rollover control for distributed electric drive multi-axle emergency rescue vehicles[J]. Journal of Traffic and Transportation Engineering, 2026, 26(7): 176-189. doi: 10.19818/j.cnki.1671-1637.2026.297
shu

Reinforcement learning anti-rollover control for distributed electric drive multi-axle emergency rescue vehicles

doi: 10.19818/j.cnki.1671-1637.2026.297
  • 1.

    School of Mechanical and Automotive Engineering, Guangxi University of Science and Technology, Liuzhou 545007, Guangxi, China

  • 2.

    State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing 100084, China

  • 3.

    School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China

  • 4.

    Liuzhou Wuling New Energy Vehicle Co., Ltd., Liuzhou 545027, Guangxi, China

  • 5.

    School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, Jiangxi, China

More Information
  • Corresponding author: SU Yan-zhao, associate researcher, PhD, E-mail: yanzhaosu66@163.com
  • Received Date: 2025-10-13
  • Accepted Date: 2026-03-23
  • Rev Recd Date: 2026-01-27
  • Publish Date: 2026-07-28
    Abstract
  • When emergency rescue vehicles perform urgent dispatch tasks on downhill and sharp-curve road sections, the gravitational component caused by the slope and the lateral inertia induced by sharp turns are likely to trigger vehicle rollover. To address this issue, an anti-rollover control strategy suitable for distributed electric-driven multi-axle emergency rescue vehicles is proposed. The strategy consists of a mode selection layer and an integrated control layer. In the mode selection layer, the lateral load transfer ratio (LTR) was used as an objective evaluation index. The vehicle rollover risk was judged according to the preset threshold, and the system was switched to the anti-rollover control mode. In the integrated control layer, a reinforcement learning controller based on the soft actor-critic (SAC) algorithm was designed to realize the coordinated control of the rear-wheel driving/braking force and the front-wheel fine-tuning angle, thereby improving the vehicle anti-rollover capability. A Python/MATLAB/TruckSim co-simulation was conducted for verification. The results show that the proposed SAC reinforcement learning anti-rollover control strategy reduces the LTR by approximately 9.7% and increases the speed by 3.9% under conditions of high initial speed and large slope; reduces the LTR by about 4.1% and increases the speed by approximately 4.5% under conditions of medium initial speed and medium slope; and reduces the LTR by around 7.8% and increases the speed by about 3.2% under conditions of low initial speed and small slope. A theoretical reference is provided for the learning-based anti-rollover control of distributed electric-driven multi-axle heavy-duty vehicles under extreme operating conditions.

     

    • FullText(HTML)
  • loading
    • References(28)
  • [1]
    ZHANG Zhen, LAI Jin-tao, YANG Xiao-guang. A priority control method for special vehicles based on heterogeneous vehicle group cooperation[J]. Journal of Traffic and Trans-portation Engineering, 2025, 25(2): 156-169. doi: 10.19818/j.cnki.1671-1637.2025.02.010
    [2]
    XU F X, ZHOU C, LIU X H. Hierarchical control strategies for multi-mode steering system of emergency rescue vehicle[J]. Mechatronics, 2022, 85: 102834. doi: 10.1016/j.mechatronics.2022.102834
    [3]
    AGYEMAN P K, TAN G F, ALEX F J, et al. Parameter matching, optimization, and classification of hybrid electric emergency rescue vehicles based on support vector machines[J]. Energies, 2022, 15(19): 7071. doi: 10.3390/en15197071
    [4]
    ZHAO D H, GONG M D, ZHAO D X, et al. Integrated control of anti-rollover for high-mobility emergency rescue vehicles[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2025, 239(5): 1455-1467. doi: 10.1177/09544070241231065
    [5]
    DUAN X H, WU J X, XIONG Y L. Dynamic emergency vehicle path planning and traffic evacuation based on SALP swarm algorithm[J]. Journal of Advanced Transportation, 2022, 2022(1): 7862746.
    [6]
    WANG P, ZHANG X Y, SHI J P, et al. Rollover prevention control of electric vehicles based on multi-objective optimi-zation coordination under extreme conditions[J]. IEEE Tran-sactions on Vehicular Technology, 2023, 72(10): 12784-12798. doi: 10.1109/TVT.2023.3274591
    [7]
    XIA Guang, LI Jia-cheng. TANG Xi-wen, et al. Research on anti-rollover control of counterweight fork lift based on roll energy classification[J]. Journal of Mechanical Engi-neering, 2023, 59(10): 275-289.
    [8]
    ZHU T M, HU M M, GUO Q H, et al. Research on anti-rollover differential braking of heavy-dump truck based on fuzzy pid control[C]//IEEE. 2023 4th International Confe-rence on Mechatronics Technology and Intelligent Manu-facturing (ICMTIM). New York: IEEE, 2023: 366-369.
    [9]
    WANG L L, ZHU J H, LIU F H, et al. Algorithm and scale experiment of gyro-based tractor rollover control towards hilly farmland application[J]. Computers and Elec-tronics in Agriculture, 2024, 220: 108925. doi: 10.1016/j.compag.2024.108925
    [10]
    NGUYEN T A. Preventing the rollover phenomenon of the vehicle by using the hydraulic stabilizer bar controlled by a two-input fuzzy controller[J]. IEEE Access, 2021, 9: 129168-129177. doi: 10.1109/ACCESS.2021.3114023
    [11]
    JEONG Y. Integrated vehicle controller for path tracking with rollover prevention of autonomous articulated electric vehicle based on model predictive control[J]. Actuators, 2023, 12(1): 41. doi: 10.3390/act12010041
    [12]
    DARBY M L, NIKOLAOU M. MPC: Current practice and challenges[J]. Control Engineering Practice, 2012, 20(4): 328-342. doi: 10.1016/j.conengprac.2011.12.004
    [13]
    TIAN Y, YAO Q Q, WANG C Q, et al. Switched model predictive controller for path tracking of autonomous vehicle consi-dering rollover stability[J]. Vehicle System Dynamics, 2022, 60(12): 4166-4185. doi: 10.1080/00423114.2021.1999990
    [14]
    ATAEI M, KHAJEPOUR A, JEON S. Model predictive control for integrated lateral stability, traction/braking con-trol, and rollover prevention of electric vehicles[J]. Vehicle System Dynamics, 2020, 58(1): 49-73. doi: 10.1080/00423114.2019.1585557
    [15]
    ZHANG B, ZHAO W Z, LUAN Z K, et al. An antirollover control strategy based on time-varying nonlinear MPC for three-axle steering/braking-by-wire vehicle[J]. IEEE Transactions on Industrial Electronics, 2024, 71(9): 11048-11060. doi: 10.1109/TIE.2023.3333010
    [16]
    SHAKYA A K, PILLAI G, CHAKRABARTY S. Reinfor-cement learning algorithms: A brief survey[J]. Expert Systems with Applications, 2023, 231: 120495. doi: 10.1016/j.eswa.2023.120495
    [17]
    ELGUEA-AGUINACO Í, SERRANO-MUÑOZ A, CHRYSO-STOMOU D, et al. A review on reinforcement learning for contact-rich robotic manipulation tasks[J]. Robotics and Computer-integrated Manufacturing, 2023, 81: 102517. doi: 10.1016/j.rcim.2022.102517
    [18]
    XIE Xian-yi, ZHAO Xin, JIN Li-sheng, et al. Trajectory tracking control of intelligent vehicles based on deep reinfor-cement learning and rolling horizon optimization[J]. Journal of Traffic and Transportation Engineering, 2024, 24(6): 259-272. doi: 10.19818/j.cnki.1671-1637.2024.06.018
    [19]
    KOH S, ZHOU B, FANG H, et al. Real-time deep reinfor-cement learning based vehicle navigation[J]. Applied Soft Computing, 2020, 96: 106694. doi: 10.1016/j.asoc.2020.106694
    [20]
    WU Chao-zhong, LENG Yao, CHEN Zhi-jun, et al. Human-machine integration method for steering decision-making of intelligent vehicle based on reinforcement learning[J]. Journal of Traffic and Transportation Engineering, 2022, 22(3): 55-67. doi: 10.19818/j.cnki.1671-1637.2022.03.004
    [21]
    MAROTTA R, STRANO S, TERZO M, et al. Enhancing roll reduction in road vehicles on uneven surfaces through the fusion of proportional control and reinforcement learning[J]. SAE International Journal of Vehicle Dynamics, Stability, and NVH, 2024, 9(1): 105-120. doi: 10.4271/10-09-01-0006
    [22]
    HARTMANN G, SHILLER Z, AZARIA A. Model-based reinforcement learning for time-optimal velocity control[J]. IEEE Robotics and Automation Letters, 2020, 5(4): 6185-6192. doi: 10.1109/LRA.2020.3012128
    [23]
    HU W M, LI X, HU J C, et al. A comprehensive driving decision-making methodology based on deep reinforcement learning for automated commercial vehicles[J]. International Journal of Automotive Technology, 2024, 25(6): 1469-1483. doi: 10.1007/s12239-024-00135-2
    [24]
    HOU X H, GAN M G, WU W, et al. Risk-conscious muta-tions in jump-start reinforcement learning for autonomous racing policy[J]. IEEE Transactions on Cybernetics, 2025, 55(2): 638-648. doi: 10.1109/TCYB.2024.3518697
    [25]
    SUKUMARAN R, PATIL H, SUBRAMANIAN S C. Diffe-rential braking based controller for mitigating un-tripped rollover in a heavy commercial road vehicle[C]//IEEE. 2023 9th International Conference on Control, Decision and Infor-mation Technologies. New York: IEEE, 2023: 1900-1905.
    [26]
    JING C Q, SHU H Y, SONG Y T. Model predictive control for integrated lateral stability and rollover prevention based on a multi-actuator control system[J]. International Journal of Control, Automation and Systems, 2023, 21(5): 1518-1537. doi: 10.1007/s12555-021-0969-0
    [27]
    ESCHMANN J. Reward function design in reinforcement learning[J]. Reinforcement Learning Algorithms: Analysis and Applications, 2021, DOI: 10.1007/978-3-030-41188-6_3.
    [28]
    MYSORE S, MABSOUT B, MANCUSO R, et al. Regula-rizing action policies for smooth control with reinforcement learning[C]//IEEE. 2021 IEEE International Conference on Robotics and Automation. New York: IEEE, 2021: 1810-1816.
    • Relative Articles
    • Supplements(0)
    • Cited By

Catalog

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (140) PDF downloads(11) Cited by()
    Related

    Website copyright Journal of Traffic and Transportation Engineering Editorial Department陕ICP备05001904号-1

    Address ：Editorial Department of Journal of Traffic and Transportation Engineering, Chang'an University, Middle Section of South 2nd Ring Road, Xi'an, China（710064） Tel：029-82334388 Email：jygc@chd.edu.cn

    All visit:Today's visit:

    Supported by: Beijing Renhe Information Technology Co. Ltd    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return