考虑交通流态势的自动驾驶车辆换道轨迹模型

doi:10.16097/j.cnki.1009-6744.2026.04.014

交通运输系统工程与信息 ›› 2026, Vol. 26 ›› Issue (4): 162-172.DOI: 10.16097/j.cnki.1009-6744.2026.04.014

• 智能交通系统与信息技术 • 上一篇下一篇

考虑交通流态势的自动驾驶车辆换道轨迹模型

何永明^{*1, 2}，那浩轩¹，金玉凤¹，张龙龙¹

1. 东北林业大学，土木与交通学院，哈尔滨 150040；2. 长沙理工大学，极端环境绿色长寿道路工程全国重点实验室（长沙），长沙 410114

收稿日期:2026-01-30 修回日期:2026-05-11 接受日期:2026-06-18 出版日期:2026-08-25 发布日期:2026-08-21
作者简介:何永明（1979— ），男，湖北广水人，副教授，博士
基金资助:
国家自然科学基金 (52572369)

Optimization Model of Lane-Changing Trajectory for Autonomous Vehicles Based on Traffic Flow Conditions

HE Yongming^{*1, 2}, NA Haoxuan¹, JIN Yufeng¹, ZHANG Longlong¹

1. School of Civil Engineering and Transportation, Northeast Forestry University, Harbin 150040, China; 2. National Key Laboratory of Green and Long-Lasting Road Engineering in Extreme Environments (Changsha), Changsha University of Science and Technology, Changsha 410114, China

Received:2026-01-30 Revised:2026-05-11 Accepted:2026-06-18 Online:2026-08-25 Published:2026-08-21
Supported by:
National Natural Science Foundation of China (52572369)

摘要/Abstract

摘要： 针对当前自动驾驶车辆换道决策多关注自身及邻近车辆，对整体交通流态势考量不足的问题，本文提出一种考虑交通流态势的换道轨迹优化模型。基于风险势场理论，将障碍车辆加速度信息融入二维高斯分布构建自适应障碍物势场，并耦合道路势场，分析动态交通环境下的风险分布特征。基于五次多项式生成换道轨迹簇，建立融合安全性、效率性、舒适性和交通流扰动的多目标代价函数，求解最优换道时间与轨迹。借助CarSim/MATLAB联合仿真平台，在60 km·h^-¹和120 km·h^-¹两类设计速度工况下对模型进行检验。仿真结果表明：自车跟踪轨迹平滑，纵向加速度峰值远低于 0.3g 的乘坐舒适性阈值；高速工况下自车速度偏差峰值较低速工况减34.9%，目标车道后车扰动可在短时内消散，模型对周围车流的扰动可控性良好。

关键词: 智能交通, 换道轨迹优化模型, 风险势场, 自动驾驶, 交通流态势

Abstract: Autonomous vehicle lane-changing decisions often focus on the ego vehicle and adjacent vehicles, overlooking overall traffic flow. This paper proposes a lane-changing trajectory optimization model involving traffic flow conditions. The risk potential field theory is used in the modeling and an adaptive obstacle potential field is constructed by embedding obstacle vehicle acceleration into a two-dimensional Gaussian distribution. A road potential field is coupled to analyze risk distribution in dynamic traffic. Lane-changing trajectories are generated with a quintic polynomial. A multi-objective cost function, which integrates safety, efficiency, comfort, and traffic flow disturbance, identifies the optimal lane-changing time and trajectory. The model is validated on a CarSim/MATLAB co-simulation platform at 60 km·h^-¹ and 120 km·h^-¹. Simulations show smooth ego vehicle tracking with peak longitudinal accelerations well below the 0.3g ride-comfort threshold. The high-speed scenario reduces the peak velocity deviation of the ego vehicle by 34.9% compared to the low-speed scenario. Transient disturbances on the target lane rear vehicles dissipate quickly, demonstrating good disturbance control of the model.

Key words: intelligent transportation, lane-changing trajectory optimization model, risk potential field, autonomous driving, traffic flow situation

中图分类号:

U491

何永明, 那浩轩, 金玉凤, 张龙龙. 考虑交通流态势的自动驾驶车辆换道轨迹模型[J]. 交通运输系统工程与信息, 2026, 26(4): 162-172.

HE Yongming, NA Haoxuan, JIN Yufeng, ZHANG Longlong. Optimization Model of Lane-Changing Trajectory for Autonomous Vehicles Based on Traffic Flow Conditions[J]. Journal of Transportation Systems Engineering and Information Technology, 2026, 26(4): 162-172.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2026.04.014

http://www.tseit.org.cn/CN/Y2026/V26/I4/162

参考文献

[1] LI G, LI Z, KNOOP V L, et al. How far ahead should autonomous vehicles start resolving predicted conflicts? Exploring uncertainty-based safety-efficiency trade off[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(10): 14183-14195.

[2] 冯天军, 郝延铭, 李飞燕, 等. 考虑驾驶风格的CAV车辆集聚换道模型[J/OL].吉林大学学报(工学版), (2025- 09- 09) [2026- 01- 25]. https://xbgxb.jlu.edu.cn/ article?type=thesis&index=0&lang=zh. [FENG T J, HAO Y M, LI F Y, et al. Clustered lane-changing model for CAV considering driving styles[J/OL]. Journal of Jilin University (Engineering and Technology Edition), (2025- 09- 09) [2026- 01- 25]. https://xbgxb.jlu.edu.cn/article? type= thesis&index=0&lang=zh.]

[3] 姜文鑫, 吴志周, 许宏鑫, 等. 基于强化学习的自动驾驶汽车换道决策研究[J]. 计算机工程与应用, 2025, 61 (12): 359-371. [JIANG W X, WU Z Z, XU H X, et al. Research on lane-changing decision-making of autonomous vehicles based on reinforcement learning[J]. Journal of Computer Engineering and Applications, 2025, 61(12): 359-371.]

[4] 刘淼淼, 刘晓晨, 朱明月, 等. 基于动态轨迹规划的自动驾驶车辆协同换道方法[J]. 交通运输系统工程与信息, 2024, 24(5): 65-78. [LIU M M, LIU X C, ZHU M Y, et al. A cooperative lane-changing method for autonomous driving vehicles based on dynamic trajectory planning[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(5): 65-78.]

[5] 程国柱, 孟凤威, 陈永胜, 等. 考虑换道风险动态评估的快速路合流区CAV换道决策模型[J]. 中国公路学报, 2025, 38(1): 268-280. [CHENG G Z, MENG F W, CHEN Y S, et al. Lane-changing decision-making model for CAVs in weaving areas of expressways considering dynamic assessment of lane- changing risk[J]. China Journal of Highway and Transport, 2025, 38(1): 268- 280.]

[6] ZHANG D, JIAO X, ZHANG T. Lane-changing and overtaking trajectory planning for autonomous vehicles with multi-performance optimization considering static and dynamic obstacles[J]. Robotics and Autonomous Systems, 2024, 182: 104797.

[7] 王可栋, 曲大义, 杨子奕, 等. 基于分子力场的网联自主车辆多目标轨迹优化方法[J/OL]. 吉林大学学报(工学版), (2025-07-11) [2026-01-25]. https://xbgxb.jlu. edu.cn/article?type=thesis&index=0&lang=zh. [WANG K D, QU D Y, YANG Z Y, et al. Multi-objective trajectory optimization method for connected and autonomous vehicles (CAVs) based on Molecular Force Field[J/OL]. Journal of Jilin University (Engineering and Technology Edition), (2025-07-11) [2026-01-25]. https://xbgxb.jlu.edu.cn/article?type=thesis & index=0 & lang=zh.]

[8] LI L, COSKUN S, FAN Y, et al. A real-time lane change trajectory planning approach for autonomous vehicles utilizing tire force prediction[J]. Mechatronics, 2025, 109: 103351.

[9] LEI Y Z, CHENG Y, YANG X T. An optimization-free approximation framework for connected and automated vehicles eco-trajectory planning under limited computing capacity[J]. Transportation Research Part C: Emerging Technologies, 2025, 171: 104949.

[10] ZHAO J, LI Y, YU Z. Re-identification and trajectory tracking of vehicles across various types of sensing facilities on expressway[J]. Expert Systems with Applications, 2025, 275: 127074.

[11] GUANGWEN T, MENGSHAN L, BIYU H, et al. Achieving accurate trajectory predicting and tracking for autonomous vehicles via reinforcement learning-assisted control approaches[J]. Engineering Applications of Artificial Intelligence, 2024, 135: 108773.

[12] CHEN H, LIU Q, SUN D, et al. Fast model predictive control trajectory tracking for autonomous vehicles based on BFGS interior point method[J]. IFAC-PapersOnLine, 2024, 58(29): 433-438.

[13] 陈峥, 张景, 陈博闻, 等. 基于异构多图时空融合的长时域车辆轨迹预测[J]. 交通运输系统工程与信息, 2025, 25(4): 126-136. [CHEN Z, ZHANG J, CHEN B W, et al. Long-time horizon vehicle trajectory prediction based on spatiotemporal fusion of heterogeneous multi-graphs[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(4): 126-136.]

[14] 佟宁, 乔亚星, 王丽智. 自动驾驶车辆基于风险场的盲区避障方法[J/OL]. 吉林大学学报(工学版), (2025-05- 21) [2026- 01- 25]. https://xbgxb.jlu.edu.cn/article?type= thesis&index=0&lang=zh. [TONG N, QIAO Y X, WANG L Z. Obstacle avoidance method for autonomous driving vehicles in blind spots based on risk field[J]. Journal of Jilin University (Engineering and Technology Edition), (2025-05-21) [2026-01-25]. https://xbgxb.jlu.edu.cn/ article?type=thesis&index=0&lang=zh.]

[15] 王国栋, 刘立, 孟宇, 等. 一体式车辆避撞轨迹规划与跟踪控制[J]. 交通运输系统工程与信息, 2022, 22(2): 127-136, 162. [WANG G D, LIU L, MENG Y, et al. Integrated trajectory planning and tracking control for vehicle collision avoidance[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(2): 127-136, 162.]

[16] 刘中姐, 赵治国, 于勤. 基于动态风险评估的车辆辅助驾驶行为决策[J]. 汽车工程, 2024, 46(11): 2005-2016. [LIU Z J, ZHAO Z G, YU Q. Behavioral decision-making for vehicle assisted driving based on dynamic risk assessment[J]. Automotive Engineering, 2024, 46(11): 2005-2016.]

[17] 王顺超, 李志斌, 曹奇, 等. 面向智能网联车辆碰撞风险规避的互动速度障碍算法[J]. 交通运输工程学报, 2023, 23(5): 264-282. [WANG S C, LI Z B, CAO Q, et al. Interactive velocity obstacle algorithm for collision risk avoidance of connected and intelligent vehicles[J]. Journal of Traffic and Transportation Engineering, 2023, 23(5): 264-282.]

[18] ZHANG Z, QIN J, TAN S, et al. Lane change trajectory planning based on improved model predictive control with artificial potential field for autonomous vehicles in medium-high speed scenarios[J]. Engineering Applications of Artificial Intelligence, 2025, 150: 110601.

[19] CEN B L, XUE Y, ZHANG K, et al. Study on traffic flows with connected vehicles and human-driven vehicles[J]. Applied Mathematics and Computation, 2025, 490: 129182.

考虑交通流态势的自动驾驶车辆换道轨迹模型

Optimization Model of Lane-Changing Trajectory for Autonomous Vehicles Based on Traffic Flow Conditions

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]	薛晴婉, 张先喆, 杨林溢, 闫睿轩, 王力. 辅助驾驶环境下融合驾驶行为熵的交叉口碰撞风险预测[J]. 交通运输系统工程与信息, 2026, 26(4): 112-123.
[2]	贾彦峰, 李富贵, 曲大义, 胡星辰, 李妍妍. 人工势场增强的网联异构车队分布式非线性纵横向耦合控制[J]. 交通运输系统工程与信息, 2026, 26(4): 148-161.
[3]	王昊, 陈旭梅. 考虑异质驾驶行为的智能网联车辆超车应对策略研究[J]. 交通运输系统工程与信息, 2026, 26(4): 173-187.
[4]	马千里, 焦乙恩, 周屹恒, 贾鹏. 机场混编摆渡车队高峰小时服务调度优化[J]. 交通运输系统工程与信息, 2026, 26(4): 321-331.
[5]	黄凯, 谢子俊, 李濠宇, 刘芯彤, 刘志远. 基于锚点分类改进的自动驾驶车道线检测研究[J]. 交通运输系统工程与信息, 2026, 26(3): 14-24.
[6]	王正礼, 唐子墨, 郑振杰. 融合检索增强生成与思维链的交通事故责任认定大模型构建[J]. 交通运输系统工程与信息, 2026, 26(3): 83-92.
[7]	姜晓红, 仲韫豪, 肖靖沂, 邢吉平, 李家伟, 华晶雯. 考虑即时零售订单的城乡公交响应式客货联运调度[J]. 交通运输系统工程与信息, 2026, 26(3): 156-165.
[8]	蒋贤才, 魏贺迪, 张馨月. 基于双智能体的交通信号与车辆轨迹动态权重联合优化[J]. 交通运输系统工程与信息, 2026, 26(3): 192-202.
[9]	徐晓美, 符蒙, 赵峻伟, 张涌. 混合交通流场景下基于改进人工势场法的队列协同换道控制[J]. 交通运输系统工程与信息, 2026, 26(3): 214-225.
[10]	张建华, 公佳豪, 张文会. 智能网联汽车复用公交车道协同控制研究[J]. 交通运输系统工程与信息, 2026, 26(3): 226-234.
[11]	曹倩霞, 陈世文, 吕松涛, 王大为. 复杂交通场景基于边缘特征增强的长队列排队检测[J]. 交通运输系统工程与信息, 2026, 26(3): 235-246.
[12]	郑展骥, 廖方正, 李燊, 冯昌奎, 凃强, 张河山, 徐进. 无人机夜间航拍视角下小目标车辆精确检测方法[J]. 交通运输系统工程与信息, 2026, 26(3): 247-258.
[13]	田君豪, 邢璐, 廖世豪, 桂瑰 , 蒋小晴. 基于地理自编码与跨域迁移的公交出行需求分层聚类方法[J]. 交通运输系统工程与信息, 2026, 26(3): 302-314.
[14]	刘少博, 苏蔚. 基于强化学习的地铁站客流动态管控策略研究[J]. 交通运输系统工程与信息, 2026, 26(3): 338-347.
[15]	王亦兵, 陈安妮, PAPAGEORGIOU Markos, 余宏鑫, 郭静秋, 章立辉. 智能网联无车道线城市道路内边界与交通信号协同控制[J]. 交通运输系统工程与信息, 2026, 26(2): 81-90.