协同换道避障模型和轨迹数据驱动的车辆协同避障策略

doi:10.13229/j.cnki.jdxbgxb.20220754

摘要/Abstract

摘要：

考虑车辆类型、驾驶风格及不同阶段影响车辆换道的关键目标，将车辆避障过程中的“车-车交互”机理描述为力的关系，构建协同换道避障模型（CLAM），提取并建立适用于突发事件的车辆避障微观轨迹数据集，将车辆避障转化为多约束优化控制问题，以优化算法（OA）为纽带，设计车辆协同避障控制（CLAM-OA）策略。结果表明：相较于数据驱动的长短时记忆模型，CLAM-OA策略输出的误差均显著减小、车速与位移在不同时域的输出结果也更加稳定。

关键词: 交通运输系统工程, 避障策略, 混合驱动, 车辆控制, 换道行为, 微观轨迹数据

Abstract:

Considering the vehicle type， driving style， and the most important objects （MIO） affecting the vehicle lane change at different stages， cooperative lane-change obstacle avoidance model （CLAM） was constructed by describing the "vehicle-vehicle interaction" mechanism in the vehicle obstacle avoidance process as a force relationship； the vehicle lane change avoidance execution events under emergencies were extracted according to the lane change execution segment extraction criterion to establish a vehicle obstacle avoidance micro-trajectory dataset to unexpected events. The cooperative vehicle lane change obstacle avoidance was transformed into a multi-constraint optimal control problem. The cooperative lane-change obstacle avoidance model-optimistic algorithm strategy （CLAM-OA strategy） was designed with the optimization algorithm as a bridge. The results show that compared with the data-driven LSTM model， the outputs of the CLAM-OA strategy have significantly lower errors and more stable results in different time domains of vehicle speed and displacement.

Key words: engineering of communication and transportation system, collision avoidance control strategy, hybrid drive, vehicle control, lane changing behavior, micro-trajectory data

中图分类号:

U491

秦雅琴,钱正富,谢济铭. 协同换道避障模型和轨迹数据驱动的车辆协同避障策略[J]. 吉林大学学报(工学版), 2024, 54(5): 1311-1322.

Ya-qin QIN,Zheng-fu QIAN,Ji-ming XIE. Vehicle cooperative obstacle avoidance strategy driven by CLAM model and trajectory data[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(5): 1311-1322.

图/表 15

图1

图2

图3

图4

图5

图6

图7

图8

表1

换道切出模型的参数分布情况"

参数	参数描述	参数范围	平均值	标准差	5%分位数	50%分位数	95%分位数
$α$	期望速度修正系数	［-9.454， 3.222］	0.075	1.492	-1.423	0.058	1.740
$β$	从众系数	［-5.360， 11.659］	0.304	2.027	-2.160	0.094	2.557
$χ$	对后车的排斥强度	［0.003， 20.488］	2.217	3.721	0.017	0.779	9.008
$δ$	对后车排斥力的作用范围	［0.172， 45.075］	10.172	11.040	0.443	6.388	34.053
$ε$	对目标车道前后车辆的排斥强度	［0， 11.963］	0.630	2.065	0.001	0.013	3.416
$?$	受目标车道车辆排斥力的作用范围	［0.046， 49.396］	6.213	9.588	0.156	2.019	22.486
$φ$	对突发障碍的排斥强度	［0.183， 42.610］	11.970	11.994	0.716	6.343	40.965
$γ$	受突发障碍排斥力的作用范围	［0.218， 53.127］	9.120	9.934	0.446	6.578	24.613

表1

表2

换道切入模型的参数分布情况"

参数	参数描述	参数范围	平均值	标准差	5%分位数	50%分位数	95%分位数
$α$	期望速度修正系数	［-1.962， 6.380］	0.088	1.181	-1.563	0.010	1.517
$β$	从众系数	［-8.203， 10.036］	-0.250	2.004	-5.681	0.049	1.487
$ε$	对目标车道前后车辆的排斥强度	［-15.487， 162.008］	2.814	10.754	-10.801	1.747	22.364
$?$	受目标车道车辆排斥力的作用范围	［0， 65.982］	19.429	9.904	1.382	19.023	32.346
$C L$	规则力修正系数	［0， 14.940］	1.928	2.847	0.092	1.076	9.232
$f$	车道线的规则力	［0， 8.832］	0.921	1.510	0.016	0.350	3.562

表2

图9

表3

表4

图10

图11

参考文献 18

1	Wang Z, Shi X W, Zhao X M, et al. Modeling decentralized mandatory lane change for connected and autonomous vehicles: an analytical method[J]. Transportation Research Part C: Emerging Technologies, 2021, 133: No. 103441.
2	Aradi S. Survey of deep reinforcement learning for motion planning of autonomous vehicles[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(2): 740-759.
3	Liu Q X, Xu S H, Lu C, et al. Early recognition of driving intention for lane change based on Recurrent Hidden Semi-Markov model[J]. IEEE Transactions on Vehicular Technology, 2020, 69(10): 10545-10557.
4	Wang H, Lu B, Li J, et al. Risk assessment and mitigation in local path planning for autonomous vehicles with LSTM based predictive model[J]. IEEE Transactions on Automation Science and Engineering, 2022, 19(4): 2738-2749.
5	Wang J J, Li Y L, Gao R X, et al. Hybrid physics-based and data-driven models for smart manufacturing: modelling, simulation, and explainability[J]. Journal of Manufacturing Systems, 2022, 63: 381-391.
6	来飞, 叶心. 汽车高速行驶时自动紧急转向避撞的前馈与反馈跟踪控制的研究[J]. 汽车工程, 2020, 42(10): 1404-1411.
	Lai Fei, Ye Xin. Research on feedforward and feedback tracking control for automatic emergency steering collision avoidance in vehicle high-speed driving[J]. Automotive Engineering, 2020, 42(10): 1404-1411.
7	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 Guo-dong, Liu Li, Meng Yu, et al. Integrated control of trajectory planning and tracking for vehicle collision avoidance[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(2): 127-136, 162.
8	彭涛, 苏丽俐, 关志伟, 等. 高速公路弯道路段车辆紧急避撞安全换道模型[J]. 汽车工程, 2019, 41(9): 1013-1020.
	Peng Tao, Su Li-li, Guan Zhi-wei, et al. A safe lane change model for vehicle emergent collision avoidance on curved section of highway[J]. Automotive Engineering, 2019, 41(9): 1013-1020.
9	韩月起, 张凯, 宾洋, 等. 基于凸近似的避障原理及无人驾驶车辆路径规划模型预测算法[J]. 自动化学报, 2020, 46(1): 153-167.
	Han Yue-qi, Zhang Kai, Yang Bin, et al. Convex approximation based a voidance theory and path planning MPC for driver-less vehicles[J]. Acta Automatica Sinica, 2020, 46(1): 153-167.
10	He X K, Liu Y L, Lyu C, et al. Emergency steering control of autonomous vehicle for collision avoidance and stabilisation[J]. Vehicle System Dynamics, 2019, 57(8): 1163-1187.
11	Lee K, Kum D. Collision avoidance/mitigation system: motion planning of autonomous vehicle via predictive occupancy map[J]. IEEE Access, 2019, 7: 52846-52857.
12	郭景华, 何智飞, 罗禹贡, 等. 人机混驾环境下基于深度学习的车辆切入轨迹预测[J]. 汽车工程, 2022, 44(2): 153-160, 214.
	Guo Jing-hua, He Zhi-fei, Luo Yu-gong, et al. Vehicle cut-in trajectory prediction based on deep learning in a human-machine mixed driving environment[J]. Automotive Engineering, 2022, 44(2): 153-160, 214.
13	秦雅琴, 钱正富, 谢济铭, 等. 基于社会力的交织区突发瓶颈段协同换道决策模型[J]. 华南理工大学学报:自然科学版, 2022, 50(7): 66-75.
	Qin Ya-qin, Qian Zheng-fu, Xie Ji-ming, et al. Cooperative lane change decision-making model of bottleneck emergency section in weaving area based on social force[J]. Journal of South China University of Technology (Natural Science Edition), 2022, 50(7): 66-75.
14	Yang D, Zhou X, Su G, et al. Model and simulation of the heterogeneous traffic flow of the urban signalized intersection with an island work zone[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(5): 1719-1727.
15	Yang X L, Yang X X, Li Y X, et al. Obstacle avoidance in the improved social force model based on ant colony optimization during pedestrian evacuation[J]. Physica A: Statistical Mechanics and its Applications, 2021, 583: No. 126256.
16	Liu S, Wang X S, Hassanin O, et al. Calibration and evaluation of responsibility-sensitive safety (RSS) in automated vehicle performance during cut-in scenarios[J]. Transportation Research Part C: Emerging Technologies, 2021, 125: No. 103037.
17	Katoch S, Chauhan S S, Kumar V. A review on genetic algorithm: past, present, and future[J]. Multimedia Tools and Applications, 2021, 80(5): 8091-8126.
18	谢济铭, 彭博, 秦雅琴. 基于换道概率分布的多车道交织区元胞自动机模型[J]. 交通运输系统工程与信息, 2022, 22(3): 276-285.
	Xie Ji-ming, Peng Bo, Qin Ya-qin. Cellular automata model of multi-lane weaving area based on lane-changing probability distribution[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(3): 276-285.

相关文章 15

[1]	张明业,杨敏,黎彧,黄世玉,李清韵. 考虑有序充电策略的多车型电动公交调度优化[J]. 吉林大学学报(工学版), 2024, 54(5): 1293-1301.
[2]	马潇驰,陆建. 基于基因表达式编程的高架道路事故实时预测[J]. 吉林大学学报(工学版), 2024, 54(3): 719-726.
[3]	严利鑫,冯进培,郭军华,龚毅轲. 不同险态情景下共驾型智能车辆接管行为特征分析[J]. 吉林大学学报(工学版), 2024, 54(3): 683-691.
[4]	曲大义,张可琨,顾原,王韬,宋慧,戴守晨. 自动驾驶车辆换道决策行为分析及分子动力学建模[J]. 吉林大学学报(工学版), 2024, 54(3): 700-710.
[5]	涂辉招,王万锦,乔鹏,郭静秋,鹿畅,吴海飞. 自动驾驶卡车路测安全员接管干预行为解析[J]. 吉林大学学报(工学版), 2024, 54(3): 727-740.
[6]	张健,李青扬,李丹,姜夏,雷艳红,季亚平. 基于深度强化学习的自动驾驶车辆专用道汇入引导[J]. 吉林大学学报(工学版), 2023, 53(9): 2508-2518.
[7]	郑植,袁佩,金轩慧,魏思斯,耿波. 桥墩复合材料柔性防撞护舷试验[J]. 吉林大学学报(工学版), 2023, 53(9): 2581-2590.
[8]	郑皓,余立均,智鹏鹏,汪忠来. 仿生扑翼微型飞行器动态避障策略[J]. 吉林大学学报(工学版), 2023, 53(9): 2732-2740.
[9]	李建华,王泽鼎. 考虑路径耗时的城市汽车分布式充电桩选点规划[J]. 吉林大学学报(工学版), 2023, 53(8): 2298-2303.
[10]	李洪涛,王琳虹,李俊达. 公路交叉口照明和限速对视觉搜索能力的影响[J]. 吉林大学学报(工学版), 2023, 53(8): 2287-2297.
[11]	巫威眺,曾坤,周伟,李鹏,靳文舟. 基于多源数据和响应面优化的公交客流预测深度学习方法[J]. 吉林大学学报(工学版), 2023, 53(7): 2001-2015.
[12]	程国柱,盛林,赵浩,冯天军. 基于危险度分析的信号交叉口专用相位设置条件[J]. 吉林大学学报(工学版), 2023, 53(7): 1962-1969.
[13]	何永明,陈世升,冯佳,万亚楠. 基于高精地图的超高速公路虚拟轨道系统[J]. 吉林大学学报(工学版), 2023, 53(7): 2016-2028.
[14]	薛志佳,王召阳,张久鹏,晏长根,许子凯,张英立,黄晓明,马涛. 泥石流作用下道路结构韧性分析及提升[J]. 吉林大学学报(工学版), 2023, 53(6): 1773-1781.
[15]	刘振亮,赵存宝,吴云鹏,马迷娜,马龙双. 数据驱动的公路桥梁网络全寿命抗震韧性评估[J]. 吉林大学学报(工学版), 2023, 53(6): 1695-1701.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

指标	CLAM-OA				LSTM
指标	纵向位移x	横向位移y	纵向速度v_x	横向速度v_y	纵向位移x	横向位移y	纵向速度v_x	横向速度v_y
MSE	0.187	0.051	0.020	0.005	24.102	0.029	9.149	0.480
RMSE	0.432	0.226	0.140	0.074	4.909	0.170	3.025	0.693
MAE	0.309	0.058	0.071	0.032	3.327	0.110	1.971	0.346
RMSPE	0.007	0.004	0.041	0.135	0.083	0.003	0.879	1.275

时域/s	CLAM-OA		LSTM
时域/s	ADE/m	FDE/m	ADE/m	FDE/m
1	0.232	0.714	0.216	2.145
2	0.353	1.053	1.444	8.173
3	0.510	1.212	3.799	18.286