Research on assisted driving functions of lane-change decision-making and trajectory tracking control considering driver dissatisfaction is carried out for autonomous lane-change scenarios on highways. First, the psychological factors of drivers were taken into account in lane-change decision-making, and a lane-change decision-making model based on driver dissatisfaction and minimum safe distance was established. Then, a lateral Linear Quadratic Regulator (LQR) controller was established based on the tracking error model to obtain the optimal feedback front wheel steering angle. Due to the problem that the weight matrices Q and R needed to be debugged repeatedly, a lateral LQR controller based on the Genetic Algorithm (GA) was proposed to obtain the optimal weight matrices Q and R, which in turn improves the robustness of the algorithm. The longitudinal LQR controller was also established to maintain the desired vehicle speed. Autonomous lane-change technology was validated using PreScan,MATLAB/Simulink and CarSim simulation platforms, and the robustness and reliability of the lateral LQR controller were verified under different fixed-speed lane-changing conditions. Under the condition of unsatisfied lane-change safety, the variable desired speed could be followed stably by the longitudinal LQR controller with a absolute value of maximum speed error of 0.69 km/h. Further comparing the lateral control performances of the LQR controller and GA+LQR controller, the lateral and heading tracking accuracies were improved by 66.7% and 27%, respectively, using the GA+LQR controller. The results confirm that the longitudinal LQR controller and the optimized GA+LQR controller have good tracking accuracies under different lane-change conditions.
车辆换道决策仿真结果如图11所示,由图11可知,在未执行换道之前,驾驶员不满意度一直积累,大于阈值之后,产生的换道意图一直存在.在15 s左右,两车的距离大于最小安全距离,满足换道条件,发出换道指令(为了描述清晰,将换道指令从1扩大至30)并执行换道,驾驶员不满意度清零,同时换道意图也消失,并在成功换道后,自车逐渐加速到目标车速100 km/h. 验证了提出的换道决策模型不仅可以正确产生换道意图,还可以保证换道过程的安全性. 在驾驶员不满意度达到阈值而不满足换道安全性时,驾驶员不满意度没有提前清空或不增长,驾驶员的换道意图也没有出现消失或震荡的现象,满足换道决策的要求.
AMMOUNS, NASHASHIBIF, LAURGEAUC .An analysis of the lane changing manoeuvre on roads:the contribution of inter-vehicle cooperation via communication[C]//2007 IEEE Intelligent Vehicles Symposium, June 13-15, 2007.Istanbul,Turkey:IEEE,2007:1095-1100.
[2]
GIPPSP G. A model for the structure of lane-changing decisions[J]. Transportation Research Part B:Methodological, 1986, 20(5): 403-414.
[3]
RATROUTN T, RahmanS M. A comparative analysis of currently used microscopic and macroscopic traffic simulation software[J]. Arabian Journal for Science and Engineering, 2009, 34: 121-133.
[4]
SEOJ, YIK. Robust mode predictive control for lane change of automated driving vehicles[R]. Warrendale: SAE Technical Paper, 2015.
[5]
CHENY Y, LIG F, LIS, et al .Exploring behavioral patterns of lane change maneuvers for human-like autonomous driving[J].IEEE Transactions on Intelligent Transportation Systems, 2022, 23(9): 14322-14335.
[6]
TALEBPOURA, MAHMASSANIH S, HAMDARS H .Modeling lane-changing behavior in a connected environment:a game theory approach[J]. Transportation Research Procedia,2015,7:420-440.
[7]
WANGX, FANJ H, LIUN .A novel decision-making algorithm of autonomous vehicle based on improved SVM[C]//Proceedings of the 2020 International Conference on Aviation Safety and Information Technology,October 14-16,2020. Weihai, China:ACM,2020:643-648.
[8]
李斌. 汽车快速行驶换道场景分析与决策方法研究[D]. 长春:吉林大学, 2020.
[9]
LIB. Research on the scenario analysis and decision-making method of the lane change during fast driving[D]. Changchun: Jilin University, 2020. (in Chinese)
CHENH, WANGJ X. A decision-making method for lane changes of automated vehicles on freeways based on drivers’ dissatisfaction[J].China Journal of Highway and Transport,2019,32(12):1-9.(in Chinese)
[12]
KUSUMAD H,ALI M, SUTANTRAN .The comparison of optimization for active steering control on vehicle using PID controller based on artificial intelligence techniques[C]//2016 International Seminar on Application for Technology of Information and Communication (ISemantic),August 5-6,2016. Semarang,Indonesia: IEEE, 2016: 18-22.
[13]
SAEEDIM A. A new robust combined control system for improving manoeuvrability, lateral stability and rollover prevention of a vehicle[J]. Proceedings of the Institution of Mechanical Engineers, Part K: Journal of Multi-body Dynamics, 2020, 234(1): 198-213.
LIY Z, LIG, ZHANGZ H. Lateral tracking control of a driverless four-wheel steering vehicle under extreme conditions[J]. Journal of Chongqing University of Technology (Natural Science),2023,37(1):66-74. (in Chinese)
[16]
YANGT, BAIZ W, LIZ Q,et al. Intelligent vehicle lateral control method based on feedforward+ predictive LQR algorithm[J].Actuators,2021,10(9): 228.
GAOL L, TANGF M, GUOP,et al. Research on improved LQR control for self-driving vehicle lateral motion[J]. Mechanical Science and Technology for Aerospace Engineering, 2021, 40(3): 435-441.(in Chinese)
[21]
SEILERP, SONGB, HEDRICKJ K. Development of a collision avoidance system[J]. Neurosurgery, 1998, 46(2): 492.
[22]
PHANT T, LEL B, NGODUYD. A cooperative space distribution method for autonomous vehicles at a lane-drop bottleneck on multi-lane freeways[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(4): 3710-3723.
[23]
SUNB H, DENGW W, WUJ,et al .Research on the classification and identification of driver’s driving style[C]//2017 10th International Symposium on Computational Intelligence and Design (ISCID), December 9-10, 2017. Hangzhou,China: IEEE, 2017: 28-32.
LIUY W. Research on lane-changing risk discrimination and personalized forewarning of expressway[D]. Xi’an:Chang’an University, 2020:10-26. (in Chinese)
[26]
PIZARRO-LERMAA O, GARCÍA-HERNÁNDEZR, SANTIBÁÑEZV A. Fine-tuning of a fuzzy computed-torque control for a 2-DOF robot via genetic algorithms[J].IFAC-PapersOnLine, 2018, 51(13): 326-331.
GUOJ H, HUP, LIL H,et al .Study on lateral fuzzy control of unmanned vehicles via genetic algorithms[J]. Journal of Mechanical Engineering, 2012, 48(6): 76-82.(in Chinese)
[29]
MARADAT, MATOUSEKR, ZUTHD .Design of linear quadratic regulator (LQR) based on genetic algorithm for inverted pendulum[J].MENDEL Soft Computing Journal,2017,23(1): 149-156.
[30]
SHIRAHATTIA, PRASADP S S, PANZADEP,et al .Optimal design of passenger car suspension for ride and road holding[J].Journal of the Brazilian Society of Mechanical Sciences and Engineering,2008,30(1):66-76.