基于时空风险场的智能车辆轨迹规划

doi:10.3969/j.issn.1004-132X.2025.10.036

摘要/Abstract

摘要：

为描述及规避智能车辆行驶时面临的不同维度风险，提出了一种基于时空风险场的双层轨迹规划方法。将交通要素划分为抽象要素和具象要素，分别建立基于高斯分布函数的抽象要素时空风险场和基于空间向量的具象要素时空风险场，以表征智能车辆在纵向、横向和时间三个维度面临的环境风险。将智能车辆的轨迹规划问题划分为路径和速度双层规划问题，分别考虑纵向-横向维度和纵向-时间维度的风险构建动态规划的代价函数，获取综合代价最低的路径和速度。结合二次规划算法对路径和速度进一步优化得到最终轨迹。仿真结果表明，所提出的方法在不同的驾驶场景下能够有效表征时空风险并规划出满足各项约束条件的行驶轨迹，从而提高道路驾驶的安全性。

关键词: 智能车辆, 时空风险场, 轨迹规划, 动态规划

Abstract:

Aming to describe and avoid different dimensions of risks faced by intelligent vehicles， a two-layer trajectory planning method was proposed based on spatio-temporal risk fields. Traffic elements were divided into abstract elements and concrete elements， the spatial-temporal risk fields of abstract elements based on Gaussian distribution function and concrete elements based on spatial vector were established respectively to represent the environmental risks faced by intelligent vehicles in three dimensions： vertical， horizontal and temporal. Additionally， the trajectory planning problem of intelligent vehicles was divided into path and speed dual planning problem. The longitudinal-lateral dimension risk and longitudinal-temporal dimension risk were accordingly applied to dynamic planning cost function. Then， the path and speed with the comprehensive lowest cost were calculated， and combined with quadratic programming algorithm， the path and velocity were further optimized to obtain the final trajectory. Simulation results demonstrate that the proposed methodology may effectively characterize spatio-temporal driving risks across diverse scenarios while generating constraint-satisfying trajectories， thereby significantly enhance road driving safety.

Key words: intelligent vehicle, spatio-temporal risk field, trajectory planning, dynamic planning

中图分类号:

U461

孔慧芳, 王晨顺, 张倩, 刘田阔. 基于时空风险场的智能车辆轨迹规划[J]. 中国机械工程, 2025, 36(10): 2463-2471.

Huifang KONG, Chenshun WANG, Qian ZHANG, Tiankuo LIU. Intelligent Vehicle Trajectory Planning Based on Spatio-temporal Risk Fields[J]. China Mechanical Engineering, 2025, 36(10): 2463-2471.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.cmemo.org.cn/CN/10.3969/j.issn.1004-132X.2025.10.036

https://www.cmemo.org.cn/CN/Y2025/V36/I10/2463

图/表 20

图1 基于时空风险场的轨迹规划架构

Fig.1 Trajectory planning architecture based on spatio-temporal risk field

图2 抽象要素时空风险场建模示意方法

Fig.2 Schematic method of spatio-temporal risk field modeling of abstract elements

图3 抽象要素时空风险场

Fig.3 Spatio-temporal risk field of abstract elements

图4 绘制时空轨迹

Fig.4 Plots spatio-temporal trajectories

图5 时空轨迹切向量与投影绘制

Fig. 5 Tangent vector and projection rendering of spatio-temporal trajectory

图6 θ角的获取

Fig.6 θ angle acquisition

图7 具象要素时空风险场

Fig.7 Spatio-temporal risk field of concrete elements

图8 时空风险场示意图

Fig.8 Schematic diagram of spatio-temporal risk field

图9 十字路口场景

Fig.9 Intersection scene

图10 ST风险图生成

Fig.10 ST risk map generation

图11 直行道路驾驶场景

Fig.11 Driving scene on a straight road

图12 直行驾驶场景时空风险

Fig.12 Spatio-temporal risk of straight-line driving scenario

图13 轨迹规划的三维视图、s-l视图及s-t视图（场景1）

Fig.13 Three-dimensional view， s-l view and s-t view of trajectory planning（scene 1）

图14 速度结果曲线（场景1）

Fig.14 Velocity result curves（scene 1）

图15 加速度结果曲线（场景1）

Fig.15 Acceleration result curves（scene 1）

图16 无信号灯十字路口驾驶场景

Fig.16 Driving scene at an intersection without traffic lights

图17 十字路口场景时空风险分布

Fig.17 Spatio-temporal risk distribution of intersection scenes

图18 轨迹规划三维视图、s-l视图及s-t视图（场景2）

Fig.18 Three-dimensional view， s-l view and s-t view of trajectory planning（scene 2）

图19 速度结果曲线（场景2）

Fig.19 Velocity result curves（scene 2）

图20 加速度结果曲线（场景2）

Fig.20 Acceleration result curves（scene 2）

参考文献 19

[1]	《中国公路学报》编辑部. 中国汽车工程学术研究综述·2023［J］. 中国公路学报， 2023， 36（11）：1-192.
	Editorial Department of China Journal of Highway and Transport. Review on China's Automotive Engineering Research Progress：2023［J］. China Journal of Highway and Transport， 2023， 36（11）：1-192.
[2]	WANG Zhaojie， LU Guangquan， TAN Haitian， et al. A Risk-field Based Motion Planning Method for Multi-vehicle Conflict Scenario［J］. IEEE Transactions on Vehicular Technology， 2024， 73（1）：310-322.
[3]	KILICARSLAN M， ZHENG Jiangyu. Predict Vehicle Collision by TTC from Motion Using a Single Video Camera［J］. IEEE Transactions on Intelligent Transportation Systems， 2019， 20（2）：522-533.
[4]	TYAGI I. Threat Assessment for Avoiding Collsions with Perpendicular Vehicles at Intersections［C］∥2021 IEEE International Conference on Electro Information Technology （EIT）. Mt. Pleasant， 2021：184-187.
[5]	MANZINGER S， PEK C， ALTHOFF M. Using Reachable Sets for Trajectory Planning of Automated Vehicles［J］. IEEE Transactions on Intelligent Vehicles， 2021， 6（2）：232-248.
[6]	ZHANG Lingtong， MA Yining， XING Xingyu， et al. Research on the Complexity Quantification Method of Driving Scenarios Based on Information Entropy［C］∥2021 IEEE International Intelligent Transportation Systems Conference （ITSC）. Indianapolis， 2021：3476-3481.
[7]	熊璐，吴建峰，邢星宇，等.自动驾驶汽车行驶风险评估方法综述［J］.汽车工程学报， 2024， 14（5）：745-759.
	XIONG Lu， WU Jianfen， XING Xinyu， et al. A Survey of Driving Risk Assessment for Autonomous Vehicles ［J］. Journal of Automotive Engineering， 2024， 14（5）：745-759.
[8]	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.
	WANG Jianqiang， WU Jian， LI Yang. Concept， Principle and Modeling of Driving Risk Field Based on Driver-Vehicle-Road Interaction［J］. China Journal of Highway and Transport， 2016， 29（1）：105-114.
[9]	LI Linheng， GAN Jing， YI Ziwei， et al. Risk Perception and the Warning Strategy Based on Safety Potential Field Theory［J］. Accident Analysis & Prevention， 2020， 148：105805.
[10]	马艳丽，秦钦，董方琦，等. 基于风险场的不同认知次任务下接管风险评估模型［J］. 汽车工程， 2024， 46（1）：9-17.
	MA Yanli， QIN Qin， DONG Fangqi， et al. Takeover Risk Assessment Model Based on Risk Field Theory under Different Cognitive Secondary Tasks［J］. Automotive Engineering， 2024， 46（1）：9-17.
[11]	褚端峰，彭赛骞，胡海洋，等.预见性驾驶风险场模型［J］. 机械工程学报， 2024， 60（10）：160-170.
	CHU Duanfeng， PENG Saiqian， HU Haiyang， et al. Predictive Driving Risk Field Model ［J］. Chinese Journal of Mechanical Engineering， 2024， 60（10）：160-170..
[12]	张志文，刘伯威，张继园，等. 麻雀搜索算法-粒子群算法与快速扩展随机树算法协同优化的智能车辆路径规划［J］. 中国机械工程， 2024， 35（6）：993-999.
	ZHANG Zhiwen， LIU Bowei， ZHANG Jiyuan， et al. Cooperative Optimization of Intelligent Vehicle Path Planning Based on PSO-SSA and RRT［J］. China Mechanical Engineering， 2024， 35（6）：993-999.
[13]	杨超，杨帆，王伟达，等. 基于时空风险的智能驾驶车辆避险决策规划［J］. 汽车工程， 2024， 46（6）：975-984.
	YANG Chao， YANG Fan， WANG Weida， et al. Risk Avoidance Decision Planning for Intelligent Driving Vehicles Based on Spatiotemporal Risk［J］. Automotive Engineering， 2024， 46（6）：975-984.
[14]	KIM D， KIM H， HUH K. Local Trajectory Planning and Control for Autonomous Vehicles Using the Adaptive Potential Field［C］∥2017 IEEE Conference on Control Technology and Applications （CCTA）. Hawaii， 2017：987-993.
[15]	HUANG Yanjun， DING Haitao， ZHANG Yubiao， et al. A Motion Planning and Tracking Framework for Autonomous Vehicles Based on Artificial Potential Field Elaborated Resistance Network Approach［J］. IEEE Transactions on Industrial Electronics， 2020， 67（2）：1376-1386.
[16]	王明强，王震坡，张雷. 基于碰撞风险评估的智能汽车局部路径规划方法研究［J］. 机械工程学报， 2021， 57（10）：28-41.
	WANG Mingqiang， WANG Zhenpo， ZHANG Lei. Local Path Planning for Intelligent Vehicles Based on Collision Risk Evaluation［J］. Journal of Mechanical Engineering， 2021， 57（10）：28-41.
[17]	WANG Mingqiang， ZHANG Lei， ZHANG Zhiqiang， et al. A Hybrid Trajectory Planning Strategy for Intelligent Vehicles in On-road Dynamic Scenarios［J］. IEEE Transactions on Vehicular Technology， 2023， 72（3）：2832-2847.
[18]	韩嘉懿. 基于驾驶人行为理解的智能汽车人机触觉交互协同转向控制研究［D］. 长春：吉林大学， 2022.
	HAN Jiayi. Research on Human-Machine Haptic Interactive Shared Steering Control Based on Driver Behavior Understanding for Intelligent Vehicle ［D］. Changchun：Jilin University， 2022.
[19]	王安杰，郑玲，李以农，等. 基于预测风险场的智能汽车主动避撞运动规划［J］. 汽车工程， 2021， 43（7）：1096-1104.
	WANG Anjie， ZHENG Ling， LI Yinong， et al. Motion Planning for Active Collision Avoidance of Intelligent Vehicles Based on Predictive Risk Field［J］. Automotive Engineering， 2021， 43（7）：1096-1104.