基于改进大脑情感学习模型的车辆纵向跟随

doi:10.13229/j.cnki.jdxbgxb20210546

摘要/Abstract

摘要：

为提高无人驾驶车辆纵向跟随控制算法的安全性，在大脑情感学习模型的基础上，删除了情感暗示信号，并结合径向基神经网络良好的非线性逼近特性，提出了一种间接自适应脑情绪神经鲁棒控制器（iARBERC）和一种证明该控制系统稳定性的Lyapunov分析方法。将其运用到单级倒立摆仿真中，并与径向基神经网络、ARBENC进行数值比较，仿真结果表明：iARBERC具有最快的响应速度、最小的跟踪误差和最优的鲁棒性能，虽然总控制能量有所提高，但偏差在4%以内。最后，将iARBERC应用到无人驾驶车辆跟随控制系统半物理仿真台架中，结果表明，搭载iARBERC的车辆对频繁变化的纵向速度有较好的跟随能力。

关键词: 无人驾驶, 纵向跟随控制, 大脑情感学习, 非线性逼近, 鲁棒性, 半物理仿真

Abstract:

In order to improve the safety of longitudinal follow-up control algorithm for unmanned vehicles， an indirect adaptive brain emotion neural robust controller （iARBERC） was proposed based on the brain emotion learning model and the good nonlinear approximation characteristics of radial basis function neural network. The stability of the control system was proved by Lyapunov analysis method. The simulation results show that iARBERC has the fastest response speed， the smallest tracking error and the best robust performance. Although the total control energy was improved， the deviation is less than 4%. Finally， iARBERC was applied to the semi-physical simulation platform of the following control system of the unmanned vehicle. The results show that the vehicle equipped with iARBERC has good following ability to the frequently changing longitudinal speed.

Key words: unmanned driving, longitudinal following, brain emotional learning, nonlinear approximation, robustness, semi-physical simulation

中图分类号:

U461.9

魏民祥,杨佳伟,陈凯,王志浩,沙朝. 基于改进大脑情感学习模型的车辆纵向跟随[J]. 吉林大学学报(工学版), 2022, 52(12): 2994-3005.

Min-xiang WEI,Jia-wei YANG,Kai CHEN,Zhi-hao WANG,Zhao SHA. Vehicle longitudinal following based on improved brain emotional learning model[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(12): 2994-3005.

图/表 27

图1

图2

表1

表2

表3

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

图15

图16

图17

图18

图19

图20

图21

图22

图23

图24

参考文献 21

1	朱敏,陈慧岩. 无人驾驶越野车辆纵向速度跟踪控制试验[J]. 机械工程学报, 2018, 54(24): 111-117.
	Zhu Min, Chen Hui-yan. Longitudinal speed tracking control test of driverless off road vehicle[J]. Chinese Journal of Mechanical Engineering, 2018, 54(24): 111-117.
2	王志文,辛鹏,孙洪涛,等. 基于收缩约束模型预测控制的无人车辆路径跟踪[J]. 控制与决策, 2022,37(3): 625-634.
	Wang Zhi-wen, Xin Peng, Sun Hong-tao, et al. Path tracking of unmanned vehicle based on shrinkage constrained model predictive control[J]. Control and Decision, 2022, 37(3): 625-634.
3	Jullierme E, Guilherme A, Reinaldo M. Longitudinal model identification and velocity control of an autonomous car[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(2): 777-786.
4	张正华. 基于神经网络的无人驾驶车辆轨迹跟踪控制[D]. 秦皇岛:燕山大学车辆与能源学院, 2019.
	Zhang Zheng-hua. Trajectory tracking control of unmanned vehicle based on neural network[D]. Qinhuangdao: School of Vehicle and Energy, Yanshan University, 2019.
5	郑小冬. 特殊道路下智能汽车自动驾驶控制策略的研究[D]. 重庆:重庆交通大学机电与车辆工程学院, 2018.
	Zheng Xiao-dong. Research on automatic driving control strategy of intelligent vehicles on special roads[D]. Chongqing:School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, 2018.
6	张家旭,王欣志,赵健,等. 汽车高速换道避让路径规划及离散滑模跟踪控制[J]. 吉林大学学报: 工学版, 2021, 51(3): 1081-1090.
	Zhang Jia-xu, Wang Xin-zhi, Zhao Jian, et al. Path planning and discrete sliding mode tracking control for vehicle high speed lane changing[J]. Journal of Jilin University (Engineering and Technology Edition), 2021, 51(3): 1081-1090.
7	Chih L, Hwang, Chang C, et al. Path tracking of an autonomous ground vehicle with different payloads by hierarchical improved fuzzy dynamic sliding-mode control[J]. IEEE Transactions on Fuzzy Systems, 2014, 26(2): 899-914.
8	任殿波,张继业. 基于Lyapunov函数方法的时滞车辆纵向跟随控制[J]. 控制与决策, 2007(8): 918-921, 926.
	Ren Dian-bo, Zhang Ji-ye. Vehicle longitudinal following control with time delay based on Lyapunov function method[J]. Control and Decision, 2007(8): 918-921, 926.
9	吴晟博,曹理想. 无人驾驶车辆轨迹跟踪控制研究[J]. 汽车实用技术, 2020(1): 51-53.
	Wu Sheng-bo, Cao Li-xiang. Research on trajectory tracking control of driverless vehicles[J]. Automotive Practical Technology, 2020(1): 51-53.
10	Chu Hong-qing, Guo Lu-lu, Chen Hong, et al. Optimal car-following control for intelligent vehicles using online road-slope approximation method[J]. Science China (Information Sciences), 2021, 64(1): 94-109.
11	Moren J, Balkenius C. A computational model of emotional learning in the amygdala[C]∥From Animals to Animats 6 Proceedings of the Sixth International Conference, Simulation of Adaptive Behavior, Cambridge, England, 2000: 67-70.
12	Moren J. Emotion and learning: a computational model of the amygdala[J]. Cybernetics and Systems, 2001, 32: 611-636.
13	Baghbani F, Akbarzadeh-T M-R, Naghibi Sistani M-B. Stable robust adaptive radial basis emotional neurocontrol for a class of uncertain nonlinear systems[J]. Neuro Computing, 2018, 309: 11-26.
14	Baghbani F, Akbarzadeh-T M-R, Naghibi Sistani M-B, et al. Emotional neural networks with universal approximation property for stable direct adaptive nonlinear control systems[J]. Engineering Applications of Artificial Intelligence, 2020, 89: No.103447.
15	Lin C M, Ramarao R, Gopalai S H. Self-organizing adaptive fuzzy brain emotional learning control for nonlinear systems[J]. International Journal of Fuzzy Systems, 2019, 21(7): 1989-2007.
16	Le T L, Huynh T T, Lin C M. Adaptive filter design for active noise cancellation using recurrent type-2 fuzzy brain emotional learning neural network[J]. Neural Computation & Application, 2020, 32: 8725-8734.
17	Akhormeh A N, Roshanian J, Moradimaryamnegari H, et al. Online and stable parameter estimation based on normalized brain emotional learning model (NBELM)[J]. Adaptive Control and Signal Processing, 2019, 33(7): 1047-1065.
18	Vahedi M, Zaeif M H, Kalat A A. A simple stable adaptive neuro-fuzzy speed controller for induction motors[J]. Intelligent and Fuzzy Systems, 2015, 29(2): 571-581.
19	Chao Fei, Zhou Da-jun, Lin Chih-min, et al. Type-2 fuzzy hybrid controller network for robotic systems[J]. IEEE Transactions on Cybernetics, 2020, 50(8): 3778-3792.
20	隋振,姜源. 基于类脑情感学习回路模型的两点预瞄驾驶员转向模型[J]. 吉林大学学报:工学版, 2020, 50(3): 1098-1105.
	Sui Zhen, Jiang Yuan. Two point preview driver steering model based on brain like emotional learning loop model[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(3): 1098-1105.
21	刘金琨. 智能控制[M]. 北京:清华大学出版社, 2019: 71-73.

相关文章 15

[1]	潘恒彦,张文会,胡宝雨,刘尊严,王永岗,张枭. 城市公交-地铁加权复合网络构建及鲁棒性分析[J]. 吉林大学学报(工学版), 2022, 52(11): 2582-2591.
[2]	金立生,郭柏苍,王芳荣,石健. 基于改进YOLOv3的车辆前方动态多目标检测算法[J]. 吉林大学学报(工学版), 2021, 51(4): 1427-1436.
[3]	刘志伟,刘建荣,邓卫. 基于潜在类别的无人驾驶汽车选择行为[J]. 吉林大学学报(工学版), 2021, 51(4): 1261-1268.
[4]	于向军,槐元辉,姚宗伟,孙中朝,俞安. 工程车辆无人驾驶关键技术[J]. 吉林大学学报(工学版), 2021, 51(4): 1153-1168.
[5]	朱晓冬,张齐贤,刘元宁,吴迪,吴祖慷,王超群,李昕龙. 基于多方向局部二值模式与稳定特征的虹膜识别[J]. 吉林大学学报(工学版), 2021, 51(2): 650-658.
[6]	曾小华,李晓建,杜劭峰,马涛,王振伟,宋大凤. 多轮混合动力驱动无人驾驶框架车整车控制器开发[J]. 吉林大学学报(工学版), 2021, 51(1): 63-71.
[7]	徐谦,李颖,王刚. 基于深度学习的行人和车辆检测[J]. 吉林大学学报(工学版), 2019, 49(5): 1661-1667.
[8]	杨顺,蒋渊德,吴坚,刘海贞. 基于多类型传感数据的自动驾驶深度强化学习方法[J]. 吉林大学学报(工学版), 2019, 49(4): 1026-1033.
[9]	许秀军, 李震, 王立权, 张同喜. 海流边界下初始铺管作业建模及半物理仿真[J]. 吉林大学学报(工学版), 2018, 48(3): 803-811.
[10]	胡云峰, 顾万里, 梁瑜, 杜乐, 于树友, 陈虹. 混合动力汽车启停非线性控制器设计[J]. 吉林大学学报(工学版), 2017, 47(4): 1207-1216.
[11]	顾万里, 张森, 胡云峰, 陈虹. 有刷直流电机非线性控制系统设计[J]. 吉林大学学报(工学版), 2017, 47(3): 900-907.
[12]	马蓓, 张海林, 张兆维, 钟鸣. 基于不完全信道信息的D2D功率分配算法[J]. 吉林大学学报(工学版), 2016, 46(4): 1320-1324.
[13]	李一兵, 常国彬, 叶方. 基于指数熵的认知无线电频谱感知算法[J]. 吉林大学学报(工学版), 2014, 44(5): 1506-1511.
[14]	孙浩, 邓伟文, 张素民, 吴梦勋. 考虑全局最优性的汽车微观动态轨迹规划[J]. 吉林大学学报(工学版), 2014, 44(4): 918-924.
[15]	王友卫, 刘元宁, 朱晓冬. 抵抗图像区域攻击的鲁棒性水印算法[J]. 吉林大学学报(工学版), 2014, 44(4): 1151-1158.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

类别		计算时间
类别		RBFNN	ARBENC（2018）	iARBERC
无干扰	max	0.0064	0.0072	0.0032
	min	3.8860×10^-4	4.0770×10^-4	4.4670×10^-4
	mean	7.6982×10^-4	7.5332×10^-4	7.1550×10^-4
正旋干扰	max	0.0064	0.0066	0.0040
	min	4.0020×10^-4	3.9870×10^-4	3.8680×10^-4
	mean	7.8781×10^-4	7.5654×10^-4	7.6305×10^-4
脉冲干扰	max	0.0103	0.0120	0.0104
	min	0.0027	0.0026	0.0024
	mean	0.0081	0.0099	0.0070
测量误差SNR=35	max	0.0442	0.0115	0.0287
	min	3.7831×10^-4	3.5920×10^-4	3.8900×10^-4
	mean	0.0011	0.0011	9.2810×10^-4

类别		MSE
类别		RBFNN	ARBENC（2018）	iARBERC
无干扰		0.001 042 374	0.001 090 652	0.000 995 991
正旋干扰		0.001 048 259	0.001 099 018	0.001 004 257
脉冲干扰		0.001 045 110	0.001 094 535	0.000 996 313
测量误差 SNR=35	mean	0.001 043 353	0.001 090 535	0.000 996 040
	max	0.001 051 434	0.001 092 145	0.001 006 870
	min	0.001 035 645	0.001 088 323	0.000 990 060

类别		J
类别		RBFNN	ARBENC（2018）	iARBERC
无干扰		11.448 6	11.295 8	11.648 9
正旋干扰		12.146 2	11.955 5	12.375 1
脉冲干扰		13.501 1	13.352 4	13.676 9
测量误差 SNR=35	mean	14.199 9	12.290 1	14.599 34
	max	14.480 1	12.471 2	14.958 85
	min	13.861 68	12.085 1	14.385 2