欢迎访问《汽车安全与节能学报》，
汽车安全与节能学报

汽车安全与节能学报 ›› 2026, Vol. 17 ›› Issue (1): 122-129.DOI: 10.3969/j.issn.1674-8484.2026.01.013

• 智能驾驶与智慧交通 • 上一篇    下一篇

融合GoT-SAC的领航—跟随式多车编队路径规划方法

王越1,2(), 段宏伟1,3, 钟薇2, 杨路3,*(), 何雷2, 柴福来1, 石晓杨1   

  1. 1.北京科技大学，机械工程学院，北京市，100083，中国
    2.清华大学，智能绿色车辆与交通全国重点实验室，北京市，100084，中国
    3.北京理工大学，机械与车辆学院，北京市，100081，中国
  • 收稿日期:2025-10-04 修回日期:2025-12-14 出版日期:2026-02-28 发布日期:2026-03-19
  • 通讯作者: 杨路，副研究员，E-mail：yanglu@bit.edu.cn。
  • 作者简介:王越，男（汉），山东，讲师。E-mail：wangyue@ustb.edu.cn。
  • 基金资助:
    国家自然科学基金项目(52202497);智能绿色车辆与交通全国重点实验室开放基金课题(KFY2413)

Path planning method for leader-follower multi-vehicle formation with integrating GoT-SAC

WANG Yue1,2(), DUAN Hongwei1,3, ZHONG Wei2, YANG Lu3,*(), HE Lei2, CHAI Fulai1, SHI Xiaoyang1   

  1. 1. School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, China
    2. State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing 100084, China
    3. School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China
  • Received:2025-10-04 Revised:2025-12-14 Online:2026-02-28 Published:2026-03-19

RichHTML

3

PDF

14

摘要：

在多车集群协同搬运任务中，为提升未知环境下编队稳定性与作业效率，基于Mecanum Wheel智能底盘硬件平台，建立融合“目标导向型变换器（GoT）”和“柔性演员与评论家（SAC）”，GoT-SAC，的领航—跟随编队式路径规划方法；并结合微缩实验平台和Gazebo仿真环境开展实验验证。结果表明：本模型在训练约95~100回合后达到收敛稳定区；与人工遥控开环同步策略相比，本方法后编队的平均相对位姿误差由18 cm降低至6 cm，路径长度差异小于5%。从而，本方法在不依赖先验地图环境中，可较好地实现稳定编队和高效避障行驶。

关键词: 多车编队控制, 领航—跟随编队式, 路径规划, 深度强化学习

Abstract:

A leader-follower formation path planning method was proposed through integrating the Goal-oriented Transformer (GoT) and the Soft Actor-Critic (SAC) on the Mecanum Wheeled intelligent platform, named GoT-SAC, to enhance the stability and efficiency of formation operation in unknown environments. Experimental validation was conducted in both the Gazebo environment and on a miniature physical platform. The results show that the GoT-SAC model convergences within 95~100 training episodes. The average relative pose error reduces from 18 cm to 6 cm with a path-length relative-difference being below 5% compared with the manual remote-control strategy. Therefore, the proposed method achieves stable formation and efficient obstacle avoidance without relying on prior map information.

Key words: multi-vehicles formation control, leader-follower formation, path planning, deep reinforcement learning

中图分类号: