基于场景复杂度分类网络与引导点机制的4WIS车辆轨迹规划方法研究

doi:10.3901/JME.260282

机械工程学报 ›› 2026, Vol. 62 ›› Issue (8): 432-449.doi: 10.3901/JME.260282

• 特邀专辑：汽车线控底盘 • 上一篇下一篇

扫码分享

基于场景复杂度分类网络与引导点机制的4WIS车辆轨迹规划方法研究

滕景佳^1,2, 李洋^1,2, 胡满江^1,2, 熊善程^1,2, 李国法³

1. 湖南大学机械与运载工程学院长沙 410082;
2. 湖南大学整车先进设计制造技术全国重点实验室长沙 410082;
3. 重庆大学机械与运载工程学院重庆 400044

收稿日期:2025-08-04 修回日期:2025-11-26 出版日期:2026-04-20 发布日期:2026-06-12
作者简介:滕景佳，男，1999年出生，博士研究生。主要研究方向为自动驾驶轨迹规划。E-mail： tengjingjia@foxmail.com;李洋(通信作者)，女，1992年出生，博士，副研究员。主要研究方向为自动驾驶轨迹规划，端到端自动驾驶。E-mail： lyxc56@gmail.com
基金资助:
国家自然科学基金资助项目(52302493)。

Research on Trajectory Planning Method for 4WIS Vehicles Based on Scene Complexity Classification Network and Guided Point Mechanism

TENG Jingjia^1,2, LI Yang^1,2, HU Manjiang^1,2, XIONG Shancheng^1,2, LI Guofa³

1. College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082;
2. State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, Hunan University, Changsha 410082;
3. College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing 400044

Received:2025-08-04 Revised:2025-11-26 Online:2026-04-20 Published:2026-06-12

摘要/Abstract

摘要： 四轮独立转向(Four-wheel independent steering，4WIS)车辆因其优越的机动性而受到广泛关注。然而现有轨迹规划方法对4WIS车辆多种运动模式、场景复杂度以及障碍物的属性考虑不足，难以发挥4WIS车辆在复杂狭窄的空间下的灵活性，导致规划效率低甚至失败。为此，本研究提出一种基于最优控制问题(Optimal control problem,OCP)的4WIS车辆轨迹规划框架。首先，提出一种基于环境图像与车辆状态信息的场景复杂度二分类网络，实现复杂/简单场景的精准识别；其次，设计面向复杂场景的轨迹规划引导策略，基于先验A^*路径构建引导点集合，将任务分解为引导点间的局部子任务提升规划效率；然后，构建面向4WIS车辆的Hybrid A^*算法，建立融合阿克曼转向、斜向移动及原地转向三种运动模式的节点扩展机制，并设计对应的节点代价函数和模式切换代价函数；最后，建立考虑障碍物属性的轨迹优化OCP框架，构建面向“可压障碍物”的逻辑约束以限制压过障碍物时的速度，提升车辆通过性的同时保障安全。仿真结果表明，在包含密集障碍物、狭窄通道和起终点位置及朝向存在显著差异的典型复杂环境下，所提方法相比传统Hybrid A^*算法成功率提高50%、通行效率提升40.26%、计算效率提升44.89%，显著提升4WIS车辆的轨迹规划性能。

关键词: 四轮独立转向车辆, 轨迹规划, 场景复杂度分类网络, 轨迹引导策略, 4WIS Hybrid A^*, 障碍物逻辑约束

Abstract: Four-wheel independent steering(4WIS) vehicles have attracted widespread attention due to their superior maneuverability. However, existing trajectory planning methods insufficiently consider the multiple motion modes of 4WIS vehicles, scene complexity, and obstacle attributes, limiting their flexibility in narrow and cluttered spaces and resulting in low planning efficiency or even failure. To address this, this study proposes a 4WIS vehicle trajectory planning framework based on an optimal control problem(OCP). First, a scene complexity binary classification network is developed based on environmental images and vehicle state information to accurately identify complex and simple scenes. Second, a trajectory guidance strategy for complex scenarios is designed, constructing a set of guided points based on a prior A^* path and decomposing the task into local subtasks between guided points to improve planning efficiency. Third, a Hybrid A^* algorithm tailored for 4WIS vehicles is constructed, incorporating a node expansion mechanism that integrates Ackermann steering, diagonal movement, and zero-turn rotation, along with corresponding node cost functions and mode-switching cost functions. Finally, a trajectory optimization OCP framework considering obstacle attributes is established, introducing logical constraints for “compressible obstacles” to limit the speed when passing over them, thereby enhancing vehicle passability while ensuring safety. Simulation results show that, in typical complex environments with dense obstacles, narrow passages, and significant differences in start and goal positions and orientations, the proposed method improves the planning success rate by 50%, increases traversal efficiency by 40.26%, and enhances computational efficiency by 44.89% compared with the Hybrid A^* algorithm, significantly boosting the trajectory planning performance of 4WIS vehicles.

Key words: four-wheel independent steering(4WIS) vehicles, trajectory planning, scene complexity classification network, trajectory guided strategy, 4WIS Hybrid A^*, obstacle logical constraints

中图分类号:

U493
TP18

滕景佳, 李洋, 胡满江, 熊善程, 李国法. 基于场景复杂度分类网络与引导点机制的4WIS车辆轨迹规划方法研究[J]. 机械工程学报, 2026, 62(8): 432-449.

TENG Jingjia, LI Yang, HU Manjiang, XIONG Shancheng, LI Guofa. Research on Trajectory Planning Method for 4WIS Vehicles Based on Scene Complexity Classification Network and Guided Point Mechanism[J]. Journal of Mechanical Engineering, 2026, 62(8): 432-449.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260282

http://www.cjmenet.com.cn/CN/Y2026/V62/I8/432

参考文献

[1] GUO J H， LUO Y G， LI K Q. An adaptive hierarchical trajectory following control approach of autonomous four-wheel independent drive electric vehicles[J]. IEEE Transactions on Intelligent Transportation Systems， 2018， 19(8)： 2482-2492.
[2] 周晨，徐飞翔. 四轮独立转向车辆转向模式切换轨迹多目标优化方法研究[J]. 机械工程学报， 2024， 60(6)： 306-320. ZHOU Chen， XU Feixiang. Multi-objective optimization method for steering mode switch trajectory of four-wheel independent steering vehicle[J]. Journal of Mechanical Engineering， 2024， 60(6)： 306-320.
[3] 赵明慧，郭浩然，张利鹏，等. 四轮独立转向分布式驱动电动汽车单轮转向失效行驶稳定性控制[J]. 机械工程学报， 2024， 60(10)： 507-522. ZHAO Minghui， GUO Haoran， ZHANG Lipeng， et al. Driving stability control of four-wheel independent steering distributed drive electric vehicle with single wheel steering failure[J]. Journal of Mechanical Engineering， 2024， 60(10)： 507-522.
[4] WAN Z H， XU C B， LI B Z， et al. Trajectory tracking method of four-wheeled independent drive and seering AGV based on LSTM-MPC and fuzzy PID cooperative control[J]. Electronics， 2025， 14(10)： 2000.
[5] 陈特，蔡英凤，陈龙，等. 基于四阶贝塞尔曲线的应急救援车辆轨迹规划方法[J]. 机械工程学报， 2025， 61(2)： 198-209. CHEN Te， CAI Yingfeng， CHEN Long， et al. Trajectory planning method of emergency rescue vehicle based on fourth-order Bezier curve[J]. Journal of Mechanical Engineering， 2025， 61(2)： 198-209.
[6] CLAUSSMANN L， REVILLOUD M， GRUYER D， et al. A review of motion planning for highway autonomous driving[J]. IEEE Transactions on Intelligent Transportation Systems， 2020， 21(5)： 1826-1848.
[7] LIU W， LI Z H， LI L， et al. Parking like a human： A direct trajectory planning solution[J]. IEEE Transactions on Intelligent Transportation Systems， 2017， 18(12)： 3388- 3397.
[8] HART P E， NILSSON N J， RAPHAEL B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics， 1968， 4(2)： 100-107.
[9] 聂士达，刘辉，廖志昊，等. 考虑复杂地形的越野环境无人车辆路径规划研究[J]. 机械工程学报， 2024， 60(10)： 261-272. NIE Shida， LIU Hui， MIAO Zhihao， et al. Study on path planning for off-road autonomous vehicles in complex terrains[J]. Journal of Mechanical Engineering， 2024， 60(10)： 261-272.
[10] LIN Z， WU K， SHEN R L， et al. An efficient and accurate A-star algorithm for autonomous vehicle path planning[J]. IEEE Transactions on Vehicular Technology， 2024， 73(6)： 9003-9008.
[11] FASSBENDER D， HEINRICH B C， WUENSCHE H J. Motion planning for autonomous vehicles in highly constrained urban environments[C] //Proc. of the 2016 IEEE/RSJ International Conference on Intelligent Robots and System (IROS)， Daejeon， Korea (South)， 2016： 4708-4713.
[12] 郭丛帅，刘辉，聂士达，等. 考虑复杂地形和障碍尺度的无人车轨迹规划[J]. 汽车工程， 2025， 47(4)： 645-657， 668. GUO Congshuai， LIU Hui， NIE Shida， et al. Trajectory planning for autonomous vehicles considering complex terrains and scales engineering obstacle[J]. Automotive， 2025， 47(4)： 645-657， 668.
[13] LI B ， ACARMAN T ， ZHANG Y M ， et al. Optimization-based trajectory planning for autonomous parking with irregularly placed obstacles： A lightweight iterative framework[J]. IEEE Transactions on Intelligent Transportation Systems， 2022， 23(8)： 11970-11981.
[14] GAO F， LIN Y， SHEN S. Gradient-based online safe trajectory generation for quadrotor flight in complex environments[C] //Proc. of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)， Vancouver， BC， Canada， 2017： 3681-3688
[15] 张鼎逆，刘毅. 基于改进遗传算法和序列二次规划的再入轨迹优化[J]. 浙江大学学报(工学版)， 2014， 48(1)： 161-167. ZHANG Dingni， LIU Yi. Reentry trajectory optimization based on improved genetic algorithm and sequential quadratic programming[J]. Journal of Zhejiang University(Engineering Science)， 2014， 48(1)： 161-167.
[16] TENG J J， LI Y， YANG Z Y， et al. User preference-aware and efficient trajectory planning for autonomous parking with hybrid A* and nonlinear optimization[C] //Proc. of the 27th International Conference on Intelligent Transportation Systems (ITSC)， 2024： 1090-1097.
[17] GUO Y Q， YAO D Y， LI B， et al. Trajectory planning for an autonomous vehicle in spatially constrained environments[J]. IEEE Transactions on Intelligent Transportation Systems， 2022， 23(10)： 18326-18336.
[18] MARTINSEN A B， LEKKAS A M， GROS S. Optimal model-based trajectory planning with static polygonal constraints[J]. IEEE Transactions on Control Systems Technology， 2022， 30(3)： 1159-1170.
[19] LIU X X， WANG W， LI X L， et al. MPC-based high-speed trajectory tracking for 4WIS robot[J]. ISA Transactions， 2022， 123： 413-424.
[20] CHANG Y， YANG Z Y， HU M J， et al. An optimal parking path planning method integrating motion mode decision-making for 4WIS vehicles*[C] //Proc. of the 27th International Conference on Intelligent Transportation Systems (ITSC)， 2024： 2570-2577.
[21] XU F X， LIU X H， ZHOU C. Dynamic switch control of steering modes for four wheel independent steering rescue vehicle[J]. IEEE Access， 2019， 7： 135595-135605.
[22] WANG D W， QI F. Trajectory planning for a fourwheel-steering vehicle[C] //Proc. of 2001 ICRA. IEEE International Conference on Robotics and Automation， Seoul， Korea (South)， 2001： 3320-3325.

基于场景复杂度分类网络与引导点机制的4WIS车辆轨迹规划方法研究

Research on Trajectory Planning Method for 4WIS Vehicles Based on Scene Complexity Classification Network and Guided Point Mechanism

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	徐飞翔, 黄振华, 王亚飞, 冯仕咏, 周晨. 基于瞬时转向中心的四轮独立转向车辆协同控制策略[J]. 机械工程学报, 2026, 62(8): 332-348.
[2]	马建伟, 李冠霖, 谢英豪, 申原同, 贾振元. 复杂曲面车削刀具轨迹轮廓偏差一致性控制方法[J]. 机械工程学报, 2026, 62(7): 452-461.
[3]	龙秀华, 胡正国, 付涛, 连楷研, 宋学官. 基于非对称多段S型曲线的矿用电铲轨迹优化[J]. 机械工程学报, 2025, 61(5): 263-274.
[4]	陈特, 蔡英凤, 陈龙, 徐兴. 基于四阶贝塞尔曲线的应急救援车辆轨迹规划方法[J]. 机械工程学报, 2025, 61(2): 198-209.
[5]	柳献, 胡秋斌, 朱雁飞, 翟一欣, 黄德中. 盾构管片自动拼装技术研究现状与展望[J]. 机械工程学报, 2025, 61(19): 183-201.
[6]	陆天尧, 尉凌霄, 曹珍珍, 刘钢, 茅健, 李军利. 锥壳展开面的自动铺丝轨迹规划优化算法[J]. 机械工程学报, 2025, 61(11): 406-416.
[7]	贺宜, 杜宇豪, 吴钪, 邱志军. 基于层次迭代搜索的自动驾驶重载半挂牵引车轨迹规划方法[J]. 机械工程学报, 2025, 61(10): 335-348.
[8]	申世全, 任锟, 李永国, 韩蕴生, 项琬婷, 耿赫阳. 金属表面异形区域上色轨迹自动规划[J]. 机械工程学报, 2024, 60(7): 258-265.
[9]	周晨, 徐飞翔. 四轮独立转向车辆转向模式切换轨迹多目标优化方法研究[J]. 机械工程学报, 2024, 60(6): 306-320.
[10]	张鹏, 尹来容, 仝永刚, 黄龙. 基于间隙预测模型的自动铺带轨迹优化方法[J]. 机械工程学报, 2024, 60(5): 296-316.
[11]	梁亮, 吴成东, 刘世昌. 基于关节损耗约束的工业机器人最优轨迹规划算法研究[J]. 机械工程学报, 2024, 60(19): 11-19.
[12]	王洪亮, 雍健羽, 皮大伟, 谢伯元, 王尔烈, 王显会. 基于贝塞尔曲线和多目标优化方法的多车队形切换轨迹规划[J]. 机械工程学报, 2024, 60(16): 270-279.
[13]	胡俊宇, 韩旭, 陶友瑞, 李珊瑚, 张建宁. 一种考虑跟随误差的S形轨迹残余振动抑制可靠性分析方法[J]. 机械工程学报, 2024, 60(16): 390-399.
[14]	戢杨杰, 张馨雨, 杨紫茹, 周上航, 黄岩军, 曹建永, 熊璐, 余卓平. 多智能网联汽车轨迹规划：现状与展望[J]. 机械工程学报, 2024, 60(10): 129-146.
[15]	梁凯冲, 赵治国, 颜丹姝, 赵坤. 基于动态运动基元的车辆高速公路换道轨迹规划[J]. 机械工程学报, 2024, 60(10): 192-206.