基于改进行车风险场与动态窗口法的无人车轨迹规划算法研究*

doi:10.16731/j.cnki.1671-3133.2026.03.009

现代制造工程 ›› 2026, Vol. 546 ›› Issue (3): 78-85.doi: 10.16731/j.cnki.1671-3133.2026.03.009

基于改进行车风险场与动态窗口法的无人车轨迹规划算法研究^*

张植钧, 刘攀, 常永强, 王守权, 马迎宸, 安慧

河南科技大学车辆与交通工程学院,洛阳 471000

收稿日期:2024-10-29 出版日期:2026-03-18 发布日期:2026-04-03
通讯作者: 刘攀,博士研究生,讲师,硕士研究生导师,主要研究方向为智能网联汽车。E-mail:19337961080@163.com
作者简介:张植钧,硕士研究生,主要研究方向为无人车轨迹规划。常永强,硕士研究生,主要研究方向为自动驾驶汽车的风险评估。
基金资助:
* 河南省自然科学基金资助项目(242300421446);青海省高原汽车电动化与智能化技术重点实验室开放课题基金项目(QZD03-202403);郑州市重大科技创新专项项目(2021KJZX0060-8)

Research on unmanned vehicle trajectory planning algorithm based on improved driving risk field and dynamic window approach

ZHANG Zhijun, LIU Pan, CHANG Yongqiang, WANG Shouquan, MA Yingchen, AN Hui

College of Vehicle and Traffic Engineering,Henan University of Science and Technology, Luoyang 471000,China

Received:2024-10-29 Online:2026-03-18 Published:2026-04-03

摘要/Abstract

摘要： 针对现有轨迹规划算法对车辆行驶风险感知能力不足从而影响避障效果的问题,提出了一种基于改进行车风险场与动态窗口法的无人车轨迹规划算法。首先,考虑车辆的尺寸和行驶方向限制对其行驶风险的影响,在车辆风险场中设计了车辆空间方位影响因子,针对行人的运动特性,构建了行人风险场模型;其次,将车辆风险场模型、行人风险场模型及道路风险场模型进行整合,得到行车统一风险场模型;然后,根据自车极限速度、性能及安全约束,构建速度采样空间,模拟速度采样空间内每组速度对应的未来一段时间内的运动轨迹,构建方位角、速度、障碍物距离及风险场强度等动态窗口法的评价函数,对轨迹进行多方面评估;最后,搭建静态避障场景和动态避障场景,进行仿真验证,结果表明,在静态避障场景和动态避障场景中,所提出算法规划的轨迹曲率峰值分别为0.017 2和0.028 0 m^-1,而对比算法规划的轨迹曲率峰值分别为0.023 6和0.035 6 m^-1,所提出算法规划的轨迹表现出更好的平滑性,同时有效保障了行车安全。

关键词: 轨迹规划, 行车风险场, 动态窗口法

Abstract: Aiming at the issue of insufficient driving risk perception in existing trajectory planning algorithms, which adversely affects obstacle avoidance performance, it proposes an unmanned vehicle path trajectory planning algorithm based on an improved driving risk field and the Dynamic Window Approach (DWA). Firstly, considering the influence of vehicle dimensions and driving direction constraints on the driving risk of motor vehicles, a spatial orientation impact factor for motor vehicles is incorporated into the vehicle risk field model. Additionally, a pedestrian risk field model is established to account for the motion characteristics of pedestrians. Subsequently, all risk field models are integrated to form a unified risk field model. Finally, based on the ego-vehicle′s maximum speed, performance limitations, and safety constraints, a velocity sampling space is constructed. For each velocity set within this space, the corresponding motion trajectory over a future time period is simulated. An evaluation function for the dynamic window approach incorporating azimuth angle, velocity, obstacle distance, and risk field intensity is developed to assess the trajectories from multiple perspectives. Static and dynamic obstacle avoidance scenarios are then set up for simulation validation. The results demonstrate that in static and dynamic obstacle scenarios, the peak trajectory curvatures planned by the proposed algorithm are 0.017 2 and 0.028 0 m^-1, respectively, whereas those planned by the comparative algorithm are 0.023 6 and 0.035 6 m^-1. The trajectories generated by the proposed algorithm exhibit superior smoothness while effectively ensuring driving safety.

Key words: trajectory planning, Driving Risk Field (DRF), Dynamic Window Approach (DWA)

中图分类号:

TP301.6

张植钧, 刘攀, 常永强, 王守权, 马迎宸, 安慧. 基于改进行车风险场与动态窗口法的无人车轨迹规划算法研究^*[J]. 现代制造工程, 2026, 546(3): 78-85.

ZHANG Zhijun, LIU Pan, CHANG Yongqiang, WANG Shouquan, MA Yingchen, AN Hui. Research on unmanned vehicle trajectory planning algorithm based on improved driving risk field and dynamic window approach[J]. Modern Manufacturing Engineering, 2026, 546(3): 78-85.

参考文献

[1] 王建强,吴剑,李洋.基于人-车-路协同的行车风险场概念、原理及建模[J].中国公路学报,2016,29(1):105-114.
[2] LI L,GAN J,JI X,et al.Dynamic driving risk potential field model under the connected and automated vehicles environment and its application in car-following modeling[J].IEEE transactions on intelligent transportation systems,2020,23(1):122-141.
[3] TIAN Y,PEI H,YANG J,et al.ITSC21 0765 FI[C]//24th IEEE International Conference on Intelligent Transportation - ITSC2021.[S.l.]:IEEE,2021.
[4] LI L,GAN J,ZHOU K,et al.A novel lane-changing model of connected and automated vehicles:Using the safety potential field theory[J].Physica A:Statistical Mechanics and its Applications,2020,559:125039.
[5] 谢春丽,刘长明.融合环境势场的动态换道轨迹规划方法研究[J].重庆理工大学学报(自然科学),2024,38(10):28-37.
[6] RECEVEUR J B,VIVTOR S,MELCHIOR P.Autonomous car decision making and trajectory tracking based on genetic algorithms and fractional potential fields[J].Intelligent Service Robotics,2020,13(2):315-330.
[7] HU S,TIAN S,ZHAO J,et al.Path planning of an unmanned surface vessel based on the improved A-Star and dynamic window method[J].Journal of Marine Science and Engineering,2023,11(5):1060.
[8] ZHOU L,WU N,CHEN H,et al.RRT^*-Fuzzy Dynamic Window Approach (RRT^*-FDWA) for Collision-Free Path Planning[J].Applied Sciences,2023,13(9):5234.
[9] TAN Z,WEI N,LIU Z.Local Path Planning for Unmanned Surface Vehicle based on the Improved DWA Algorithm[C]//2022 41st Chinese Control Conference (CCC).[S.l.]:IEEE,2022:3820-3825.
[10] 高群森.面向无人方程式赛车的道路感知和轨迹规划算法研究[D].西安:长安大学,2023.
[11] 丁嘉纯,田杰.无人车换道轨迹与跟踪控制研究[J].重庆理工大学学报(自然科学),2024,38(4):72-78.
[12] 刘东,聂枝根,周贻.复杂交通环境下的智能汽车局部轨迹规划方法的研究[J].重庆理工大学学报(自然科学),2023,37(4):39-49.
[13] 杜卓洋.无人驾驶车辆轨迹规划算法研究[D].杭州:浙江大学,2019.
[14] WANG S,LIN F,WANG T,et al.Autonomous vehicle path planning based on driver characteristics identification and improved artificial potential field[C]//Actuators.[S.l.]:MDPI,2022.
[15] 张垚,彭育辉.无人驾驶汽车离散优化的轨迹规划算法[J].福州大学学报(自然科学版),2021,49(4):508-515.
[16] 于越.基于时空联合规划的无人车轨迹规划算法研究[D].长春:吉林大学,2024.
[17] 贺勇,侯体成,曾子望.融合改进A^*和动态窗口法的无人机路径规划[J/OL].机械科学与技术:1-9[2024-03-26].https://doi.org/10.13433/j.cnki.1003-8728.20230322.
[18] 李光泽,俞万能,廖卫强,等.基于动态窗口法的近海水域船舶避障算法研究[J].中国舰船研究,2024,19(1):230-237.
[19] LI Y,ZHU Q.Local path planning based on improved dynamic window approach[C]//2021 40th Chinese Control Conference (CCC).[S.l.]:IEEE,2021:4291-4295.
[20] YAO M,DENG H,FENG X,et al.Improved dynamic windows approach based on energy consumption management and fuzzy logic control for local path planning of mobile robots[J].Computers & Industrial Engineering,2024,187:109767.
[21] 张琳,薛建儒,马超,等.高速公路无人驾驶的分层抽样多动态窗口轨迹规划算法[J].自动化学报,2024,50(7):1315-1332.
[22] 朱乃宣,高振海,胡宏宇,等.基于交通风险评估的个性化换道触发研究[J].汽车工程,2021,43(9):1314-1321.
[23] 吴剑.考虑人—车—路因素的行车风险评价方法研究[D].北京:清华大学,2015.
[24] WOLF M T,BURDICK J W.Artificial potential functions for highway driving with collision avoidance[C]//2008 IEEE
International Conference on Robotics and Automation.[S.l.]:IEEE,2008:3731-3736.
[25] LI H,LI S,XIA F,et al.Driving risk field modeling and the influencing factors analysis for intelligent connected vehicle[C]//International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2021).[S.l.]:SPIE, 2022.

基于改进行车风险场与动态窗口法的无人车轨迹规划算法研究^*

Research on unmanned vehicle trajectory planning algorithm based on improved driving risk field and dynamic window approach

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

[1]	杨骏泽, 孙丹枫, 赵建勇. 基于混沌变异粒子群算法的工业机器人轨迹规划^*[J]. 现代制造工程, 2026, 546(3): 20-28.
[2]	余风军, 周晓平. 基于改进A^*-DWA算法的移动机器人避障技术[J]. 现代制造工程, 2026, 545(2): 30-34.
[3]	景会成, 张冰珂, 张靖轩, 郭明亮, 孙晋超. 基于改进粒子群算法的焊接机械臂轨迹规划方法^*[J]. 现代制造工程, 2025, 537(6): 67-72.
[4]	李建儒, 龚堰珏, 赵罘. 基于混合遗传粒子群算法的机器人关节空间轨迹规划^*[J]. 现代制造工程, 2025, 537(6): 84-91.
[5]	金桥, 杨光锐, 王霄, 徐凌桦, 张芳. 基于A-TD3的码垛机器人轨迹规划^*[J]. 现代制造工程, 2025, 536(5): 42-52.
[6]	刘震, 张洪. 融合改进双向A^*与动态窗口法的仓储移动机器人路径规划[J]. 现代制造工程, 2025, 536(5): 99-105.
[7]	付丹丹, 李波. 基于改进RRT^与DWA融合的移动机器人路径规划算法研究^[J]. 现代制造工程, 2025, 535(4): 91-97.
[8]	许家伟, 李磊, 汪建华, 张雅君, 覃杰伟, 刘旭珍. 基于TCSPSO算法的机械臂运动时间最优轨迹规划^*[J]. 现代制造工程, 2025, 534(3): 69-76.
[9]	刘德, 陈涛, 赵旭峰. 半开式整体叶轮流道多轴插铣轨迹规划研究[J]. 现代制造工程, 2025, 542(11): 94-99.
[10]	马国庆, 刘启畅, 刘珺玮, 曲合拉·金恩斯. 基于点云的航发叶片分割及打磨轨迹规划方法^*[J]. 现代制造工程, 2024, 523(4): 102-108.
[11]	孔慧芳, 刘润武, 胡杰. 基于多模态中间表示的端到端自动驾驶模型^*[J]. 现代制造工程, 2024, 522(3): 70-78.
[12]	张学聪, 晁永生, 李纯艳, 周江林. 基于机器学习的工业机器人多目标轨迹规划^*[J]. 现代制造工程, 2024, 521(2): 31-37.
[13]	陈广玲, 张天赐, 付涛, 王林涛, 宋学官. 基于NSGA-Ⅱ的智能化电铲多目标最优挖掘轨迹规划[J]. 现代制造工程, 2024, 521(2): 142-149.
[14]	金宇杰, 龚堰珏, 赵罘. 基于模拟退火量子遗传算法的焊接机器人轨迹规划^*[J]. 现代制造工程, 2024, 520(1): 33-38.
[15]	何成刚;朱润智;黄挺博;汪晓鑫;黄尊地;刘吉华. 工业机器人轨迹规划与优化研究进展[J]. 现代制造工程, 2023, 514(7): 150-159.