现代制造工程Issue(3)：78-85,161,9.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
Research on unmanned vehicle trajectory planning algorithm based on improved driving risk field and dynamic window approach
摘要
Abstract
Aiming at the issue of insufficient driving risk perception in existing trajectory planning algorithms,which adversely af-fects 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 driv-ing 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-ve-hicle's maximum speed,performance limitations,and safety constraints,a velocity sampling space is constructed.For each ve-locity 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 ensu-ring driving safety.关键词
轨迹规划/行车风险场/动态窗口法Key words
trajectory planning/Driving Risk Field(DRF)/Dynamic Window Approach(DWA)分类
信息技术与安全科学引用本文复制引用
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,(3):78-85,161,9.基金项目
河南省自然科学基金资助项目(242300421446) （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) （QZD03-202403）
郑州市重大科技创新专项项目(2021KJZX0060-8) （2021KJZX0060-8）
