|Table of Contents|

Lane-changing trajectory planning for heterogeneous drivers based on multivariate benefits(PDF)

长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2025年4期
Page:
153-165
Research Field:
交通工程
Publishing date:

Info

Title:
Lane-changing trajectory planning for heterogeneous drivers based on multivariate benefits
Author(s):
LONG Xue-qin;  MAO Jian-xu;  WANG Yuan-ze;  ZHAI Man-rong
(College of Transportation Engineering, Chang'an University, Xi'an 710064, Shaanxi, China)
Keywords:
traffic engineering;  dynamic planning of lane-changing trajectory;  quintic polynomial;  driving behavior;  driving style
PACS:
U491
DOI:
10.19721/j.cnki.1671-8879.2025.04.013
Abstract:
According to the characteristics of driver style's real-time changes and diverse lane-changing requirements, a dynamic lane-changing trajectory planning method considering drivers' short-term driving styles was proposed. First, the key feature variables affecting the lane-changing behavior were obtained based on the eXtreme Gradient Boosting algorithm, and drivers were classified into conservative, ordinary, and aggressive types using a clustering algorithm. Then, safety and comfort indicators were proposed, and benefit functions of trajectory planning for the three styles of drivers were constructed. Next, the quintic polynomial method was adopted to establish longitudinal and lateral trajectory planning models separately, and the trajectory was adjusted in real time based on the motion states of surrounding vehicles. Finally, the deviations between the planned trajectory and the actual trajectory, and the planned trajectories for different styles of drivers were compared. Results show that, compared to the actual trajectory, the longitudinal deviation of the planned trajectory is less than 5 m for most drivers, while the lateral deviation is mostly concentrated between 0.77 m and 0.90 m for most drivers. The average minimum headway distance of the planned trajectory increases from 34.39 m to 47.53 m, and the average maximum difference of acceleration decreases from 0.45 m/s2 to 0.17 m/s2, demonstrating the safety and comfort of the planned trajectory. Significant differences exist among the planning trajectories of different types of drivers, validating the correctness of the driving style classification. This research considers the short-time variability of driving style and the differing demands of various driver styles regarding safety and comfort. It can calculate the optimal trajectory for different driving styles, providing theoretical support for enhancing lane-changing comfort and safety.7 tabs, 11 figs, 25 refs.

References:

[1] 李 硕,杨晓芳.基于元胞自动机的竞争型换道模型[J].交通运输研究,2018,4(4):9-15.
LI Shuo, YANG Xiao-fang. A competitive channel change model based on cellular automata[J]. Transportation Research, 2018,4(4): 9-15.
[2]SHARMA A, ZHENG Z D, BHASKARA A. A pattern recognition algorithm for assessing trajectory completeness[J]. Transportation Research Part C: Emerging Technologies, 2018, 96: 432-457.
[3]陆 建,李英帅.车辆换道行为建模的回顾与展望[J].交通运输系统工程与信息,2017,17(4):48-55.
LU Jian, LI Ying-shuai. Review and perspective of the modeling of vehicle lane changing behavior[J]. Transportation System Engineering and Information, 2017,17(4): 48-55.
[4]冯 耀,景首才,惠 飞,等.基于深度强化学习的智能网联车辆换道轨迹规划方法[J].汽车安全与节能学报,2022,13(4):705-717.
FENG Yao, JING Shou-cai, HUI Fei, et al. Track change track planning method for intelligent connected vehicles based on deep reinforcement learning[J]. Journal of Automotive Safety and Energy Conservation, 2022,13(4): 705-717.
[5]李伟东,李 乐.基于改进RRT算法的无人车路径规划[J].计算机测量与控制,2023,31(1):160-166.
LI Wei-dong, LI Le. Unmanned vehicle path planning based on an improved RRT algorithm[J]. Computer measurement and control, 2023,31(1): 160-166.
[6]ZHANG J, WU J, SHEN X, et al. Autonomous land vehicle path planning algorithm based on improved heuristic function of A-star[J]. International Journal of Advanced Robotic Systems, 2021, 18(5): 1-10.
[7]王 莹,卫 翀,马 路.基于二次规划的智能车辆动态换道轨迹规划研究[J].中国公路学报,2021,34(7):79-94.
WANG Ying, WEI Chong, MA Lu. Research on dynamic lane change trajectory planning of intelligent vehicles based on secondary planning[J]. Highway Journal of China, 2021, 34(7): 79-94.
[8]汪海松,胡明辉,黎万洪,等.建立安全换道域的换道决策与规划[J].重庆大学学报,2024,47(3):16-29.
WANG Hai-song, HU Ming-hui, LI Wan-hong, et al. Establish the lane change decision and planning of safe lane change domain[J]. Journal of Chongqing University, 2024, 47(3): 16-29.
[9]ALBERTO D, MIGUEL C, FELIPE J, et al. Modelling the human lane-change execution behavior through multilayer perceptrons and convolutional neural networks[J]. Transportation Research Part F: Psychology and Behaviour, 2018, 56: 134-148.
[10]DENG H, WANG J, YANG J, et al. Study on automatic lane change trajectory control of intelligent vehicle on expressway[J]. Journal of Physics: Conference Series, 2023, 2480(1): 012003.
[11]潘兵宏,章泽龙,周 乾,等.基于sigmoid换道模型的匝道连续分流间距[J].长安大学学报(自然科学版),2023,43(6):37-48.
PAN Bing-hong, ZHANG Ze-long, ZHOU Qian, et al. Continuous diversion spacing of ramps based on sigmoid lane-change mode[J]. Journal of Chang'an University(Natural Science Edition), 2023, 43(6): 37-48.
[12]唐 斌,许占祥,江浩斌,等.基于分段优化的车辆换道避障轨迹规划[J].汽车工程,2022,44(6):831-841.
TANG Bin, XU Zhan-xiang, JIANG Hao-bin, et al. Vehicle lane change and obstacle avoidance trajectory planning based on segment optimization[J]. Automotive Engineering, 2022,44(6): 831-841.
[13]温惠英,张伟罡,赵 胜.基于生成对抗网络的车辆换道轨迹预测模型[J].华南理工大学学报(自然科学版),2020,48(5):32-40.
WEN Hui-ying, ZHANG Wei-gang, ZHAO Sheng. Prediction model of vehicle lane switching trajectory based on the generated adversarial network[J]. Journal of South China University of Technology(Natural Science Edition), 2020,48(5): 32-40.
[14]CHRISTOPH H, WERNER K, JENS N, et al. Passengers comfort during automated motorway lane changes: A subject study on different lane change trajectories at the Stuttgart driving simulator[J]. Automotive and Engine Technology, 2022, 7(3/4): 343-351.
[15]LI X, GUO Z, SU D, et al. Time-dependent lane change trajectory optimization considering comfort and efficiency for lateral collision avoidance[J]. IET Intelligent Transport Systems, 2021, 15(5): 595-605.
[16]WANG X, QIN X, ZHANG H, et al. Cognitive granular-based path planning and tracking for intelligent vehicle with multi-segment Bezier curve stitching[J]. Intelligent Automation & Soft Computing, 2023, 37(1): 385-400.
[17]赵树恩,王金祥,李玉玲.基于多目标优化的智能车辆换道轨迹规划[J].交通运输工程学报,2021,21(2):232-242.
ZHAO Shu-en, WANG Jin-xiang, LI Yu-ling. Track-changing trajectory planning of intelligent vehicles based on multi-objective optimization[J]. Journal of Transportation Engineering, 2021,21(2): 232-242.
[18]尚 婷,吴 鹏,唐伯明,等.隧道至互通小间距路段车辆换道博弈行为研究[J].中国安全科学学报,2021,31(10):68-75.
SHANG Ting, WU Peng, TANG Bo-ming, et al. Study on the game behavior of tunnel to interchange[J]. Chinese Journal of Safety Science, 2021,31(10): 68-75.
[19]张雅丽,付 锐,袁 伟,等.考虑能耗的进出站驾驶风格分类及识别模型[J].吉林大学学报(工学版), 2023,53(7):2029-2042.
ZHANG Ya-li, FU Rui, YUAN Wei, et al. The driving style classification and identification model[J]. Journal of Jilin University(Engineering Edition), 2023, 53(7): 2029-2042.
[20]汪 猛.基于高精度数据的换车道行为特征研究[D].长沙:湖南大学,2017.
WANG Meng. Study on the behavior characteristics of lane changing based on high-precision data[D]. Changsha: Hunan University, 2017.
[21]贾寒冰,刘 鹏,张 雷,等.基于规则与机器学习融合的换道决策建模方法研究[J].机械工程学报,2022,58(4):212-221.
JIA Han-bing, LIU Peng, ZHANG Lei, et al. Research on the lane-change decision modeling method based on the fusion of rules and machine learning[J]. Journal of Mechanical Engineering, 2022, 58(4): 212-221.
[22]董俊一.考虑驾驶风格的智能驾驶换道决策模型研究[D].长春:吉林大学,2022.
DONG Jun-yi. Study of intelligent driving considering driving style[D]. Changchun: Jilin University, 2022.
[23]ALI Y, ZHENG Z, HAQUE M M, et al. A game theory-based approach for modelling mandatory lane-changing behaviour in a connected environment[J]. Transportation Research Part C, 2019, 106: 220-242.
[24]郝艳军.基于自然驾驶的换道意图识别及轨迹预测研究[D].西安:长安大学,2022.
HAO Yan-jun. Research on lane change intention recognition and trajectory prediction based on natural driving[D]. Xi'an: Chang'an University, 2022.
[25]周荣贵,高 沛,李雨璇,等.基于轨迹数据的高速公路小客车异常驾驶行为[J].吉林大学学报(工学版),2024,54(9):2581-2587.
ZHOU Rong-gui, GAO Pei, LI Yu-xuan, et al. Anomalous driving behavior threshold of highway passenger cars based on trajectory data[J]. Journal of Jilin University(Engineering Edition), 2024,54(9):2581-2587.

Memo

Memo:
-
Last Update: 2025-07-25