无级转向履带车辆驾驶员转向操控行为建模与预测

doi:10.12382/bgxb.2024.0877

摘要/Abstract

摘要：

基于现役有人驾驶履带车辆进行无人化改造是无人履带车辆研制的有效技术途径之一。为实现某现役履带车辆无人化线控技术改造,设计车辆数据采集系统,以实现车辆状态数据与驾驶员操控数据的同步采集。依据人类驾驶员的操控数据,基于高斯混合模型对驾驶员转向操控行为进行聚类分析,并建立转向操控行为概率模型。基于不同转向类别,以车辆行驶速度和航向角偏差为模型输入,以静液马达摆臂转角为转向操控量预测真值,对驾驶员转向操控预测模型进行训练,实现对驾驶员转向操控行为准确预测,并在真实越野场景下进行验证。试验结果表明,所提转向操控预测模型可以准确地预测驾驶员转向操控。

关键词: 履带车辆, 操控行为, 行为预测, 高斯混合模型, 随机森林

Abstract:

Reforming the current manned tracked vehicles into the unmanned tracked vehicles is one effective way to develop the unmanned tracked vehicle.To this end,a data acquisition system is designed to collect the vehicle state and driver’s operation data.Based on the collected data,the driver’s steering behaviors during the tracked vehicle’s operation are clustered and analyzed based on the Gaussian mixture model(GMM),and a steering control behavior model is established.Based on different steering categories from GMM,a prediction model for the driver’s steering operation is trained by taking the running speed and steering angle deviation of vehicle as model inputs and the turning angle of hydraulic motor swinging arm as the predictive truth value of steering control.The proposed predsiction model is used for the statistical modeling and prediction of driver steering behavior in the in real cross-country environment.Experimental results show that the proposed steering control model can predict the driver’s steering behavior accurately.

Key words: tracked vehicle, steering behavior, behavior prediction, Gaussian mixture model, random forest

杜云生, 王文硕, 魏源, 陈慧岩. 无级转向履带车辆驾驶员转向操控行为建模与预测[J]. 兵工学报, 2024, 45(S2): 162-169.

DU Yunsheng, WANG Wenshuo, WEI Yuan, CHEN Huiyan. Modeling and Prediction of Driver’s Steering Control Behavior for Stepless Steering Tracked Vehicle[J]. Acta Armamentarii, 2024, 45(S2): 162-169.

图/表 13

图1 无级转向履带车辆

Fig.1 Stepless steering tracked vehicle

图2 无级转向履带车辆传动系统

Fig.2 Transmission system of continuously stepless steering tracked vehicles

图3 数据采集系统连接示意图

Fig.3 Connection diagram of data acquisition system

图4 驾驶员操控动作视觉传感器布置

Fig.4 Arrangement of driver control action vision sensor

图5 驾驶员转向操控行为预测模型

Fig.5 Driver steering behavior prediction model

图6 驾驶员转向操控装置

Fig.6 Driver steering control device

图7 随机森林算法

Fig.7 Random forest algorithm

图8 试验场地

Fig.8 Experimental site

图9 驾驶员转向操控预测模型训练流程

Fig.9 Training process of driver steering prediction model

图10 静液马达摆臂转角数据值与方向盘对应关系

Fig.10 The corresponding relationship between the turning angle data of hydrostatic motor swinging arm and the steering wheel

表1 左转行驶聚类结果

Table 1 Clustering results of left-turn driving

转向类别	均值/(°)	标准差/(°)
直线行驶	18.51	0.41
小曲率转向	16.61	1.33
中等曲率转向	12.46	1.20
大曲率转向	7.76	4.38

图11 左转行驶的概率密度

Fig.11 Probability density of left turning

图12 转向操控预测结果

Fig.12 Results of steering control prediction

参考文献 12

[1]	李林林, 张承龙, 卓志敏. 智能无人作战系统发展及关键技术[J]. 现代防御技术, 2020, 48(3):37-43. doi: 10.3969/j.issn.1009-086x.2020.03.006
	LI L L, ZHANG C L, ZHUO Z M. Development and key technology of intelligent unmanned combat system[J]. Modern Defence Technology, 2020, 48(3):37-43. (in Chinese)
[2]	YANG S, ZHENG H Y, WANG J M, et al. A personalized human-like lane-changing trajectory planning method for automated driving system[J]. IEEE Transactions on Vehicular Technology, 2021, 70(7):6399-6414.
[3]	XIE S S, CHEN S T, TOMIZUKA M, et al. To develop human-like automated driving strategy based on cognitive construction:appraisal and perspective[C]// Proceedings of the 2020 IEEE 23rd International Conference on Intelligent Transportation Systems.Washington,DC,US:IEEE, 2020.
[4]	王博洋, 龚建伟, 高天云, 等. 基于高斯混合-隐马尔可夫模型的速差转向履带车辆横向控制驾驶员模型[J]. 兵工学报, 2017, 38(12):2301-2308. doi: 10.3969/j.issn.1000-1093.2017.12.002
	WANG B Y, GONG J W, GAO T Y, et al. Steering control driver model of skid steering vehicle based on Gaussian mixture model-hidden Markov model[J]. Acta Armamentarii, 2017, 38(12):2301-2308. (in Chinese)
[5]	王博洋, 龚建伟, 熊光明, 等. 有级转向履带车辆的驾驶员操控行为模型[J]. 兵工学报, 2020, 41(12):2379-2388.
	WANG B Y, GONG J W, XIONG G M, et al. Driver control behavior model for tracked vehicle with stepped steering mechanism[J]. Acta Armamentarii, 2020, 41(12):2379-2388. (in Chinese) doi: 10.3969/j.issn.1000-1093.2020.12.002
[6]	刘庆霄, 唐泽月, 张超朋, 等. 基于高斯混合-隐半马尔可夫模型的双侧独立电驱动无人履带机动平台纵向决策方法[J]. 兵工学报, 2022, 43(8):1733-1743.
	LIU Q X, TANG Z Y, ZHANG C P, et al. Research on GMM-HSMM-based longitudinal decision-making system for two-side independent electric unmanned tracked platform[J]. Acta Armamentarii, 2022, 43(8):1733-1743. (in Chinese)
[7]	PARK J, ZAHABI M. A review of human performance models for prediction of driver behavior and interactions with in-vehicle technology[J]. Human Factors, 2024, 66(4):1249-1275.
[8]	PAKDAMANIAN E, SHENG S L, BAEE S, et al. Deeptake:prediction of driver takeover behavior using multimodal data[C]// Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems.Yokohama, Japan: Association for Computing Machinery, 2021:1-14.
[9]	XU W X, WANG J H, FU T, et al. Aggressive driving behavior prediction considering driver’s intention based on multivariate-temporal feature data[J]. Accident Analysis & Prevention, 2022, 164:106477.
[10]	LI G F, YANG L, LI S, et al. Human-like decision making of artificial drivers in intelligent transportation systems:an end-to-end driving behavior prediction approach[J]. IEEE Intelligent Transportation Systems Magazine, 2021, 14(6):188-205.
[11]	AZADANI M N, BOUKERCHE A. Siamese temporal convolutional networks for driver identification using driver steering behavior analysis[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10):18076-18087.
[12]	WANG J X, FANG Z W, DAI M M, et al. Robust steering assistance control for tracking large-curvature path considering uncertainties of driver’s steering behavior[J]. Proceedings of the Institution of Mechanical Engineers,Part D:Journal of Automobile Engineering, 2021, 235(7):2013-2028.

[1]	聂维, 何洪文, 雷强顺, 万义强. 基于键合图法的履带车油气弹簧阻尼阀特性分析[J]. 兵工学报, 2024, 45(8): 2728-2736.
[2]	吴锐, 于会龙, 董昊天, 席军强. 履带式特种车辆精细化动力学建模与仿真[J]. 兵工学报, 2024, 45(5): 1384-1401.
[3]	袁艺, 盖江涛, 曾根, 周广明, 李训明, 马长军. 高速履带车辆横摆运动响应特性分析与试验验证[J]. 兵工学报, 2024, 45(4): 1094-1107.
[4]	李欢欢, 刘辉, 盖江涛, 李训明. 基于粒子群优化算法PID参数优化的双电机耦合驱动履带车辆转向控制[J]. 兵工学报, 2024, 45(3): 916-924.
[5]	王绪, 李睿, 黄英, 沈继伟, 商显赫. 考虑不同路面特征的军用履带车辆循环工况构建[J]. 兵工学报, 2024, 45(3): 907-915.
[6]	李耀恒, 盖江涛, 张楠, 成城, 李翠芬, 帅志斌, 刁利军. 电传动履带车辆电气系统稳定性分析及优化提升策略[J]. 兵工学报, 2024, 45(10): 3397-3414.
[7]	刘佳, 刘海鸥, 陈慧岩, 毛飞鸿. 基于融合特征的无人履带车辆道路类型识别方法[J]. 兵工学报, 2023, 44(5): 1267-1276.
[8]	卢佳兴, 刘海鸥, 关海杰, 李德润, 陈慧岩, 刘龙龙. 基于双参数自适应优化的无人履带车辆轨迹跟踪控制[J]. 兵工学报, 2023, 44(4): 960-971.
[9]	曾子豪, 张京东, 龚雪莲, 刘坤明, 桂学文, 廖日东. 拉伸载荷下双销式履带板强度计算方法[J]. 兵工学报, 2023, 44(3): 831-840.
[10]	任济寰, 吴祥, 薄煜明, 吴盘龙, 何山. 基于增强上下文信息长短期记忆网络的弹道轨迹预测[J]. 兵工学报, 2023, 44(2): 462-471.
[11]	生辉, 项昌乐, 盖江涛, 袁艺, 简洪超, 张楠. 双侧电机耦合驱动履带车辆单侧电机故障模式下车辆安全控制[J]. 兵工学报, 2023, 44(11): 3498-3507.
[12]	陶俊峰, 刘海鸥, 关海杰, 陈慧岩, 臧政. 基于可通行度估计的无人履带车辆路径规划[J]. 兵工学报, 2023, 44(11): 3320-3332.
[13]	张发平, 张书畅, 武锴, 张云贺, 阎艳. 基于代理模型进化的履带车辆动力学参数优化[J]. 兵工学报, 2023, 44(1): 27-39.
[14]	周铖, 罗杨, 魏江, 曹宏瑞, 兰海, 张万昊. 履带车辆制动器扭振信号瞬时频率特征提取方法研究[J]. 兵工学报, 2023, 44(1): 316-324.
[15]	袁艺, 盖江涛, 周广明, 高秀才, 李训明, 马长军. 高速电驱动履带车辆操纵特性分析[J]. 兵工学报, 2023, 44(1): 203-213.