正在加载图片...
工程科学学报.第44卷,第2期:235-243.2022年2月 Chinese Journal of Engineering,Vol.44,No.2:235-243,February 2022 https://doi.org/10.13374/j.issn2095-9389.2021.04.23.001;http://cje.ustb.edu.cn 神经网络在无人驾驶车辆运动控制中的应用综述 张守武2),王恒),陈鹏,张笑语),李擎1,)区 1)北京科技大学自动化学院,北京1000832)北京城市学院信息学部,北京1000833)工业过程知识自动化教育部重点实验室,北京 100083 区通信作者,E-mail:liqing@ies.ustb.edu.cn 摘要无人驾驶车辆自身具有强烈的非线性、信号时延和参数不确定性,对它的控制还受到道路附着系数的变化、侧向风 等外界因素影响.因此传统控制方法往往难以对其稳定和精确地控制.神经网络所具有的学习能力、自适应能力和近似非线 性映射的能力,为解决车辆模型参数的不确定性、外界的扰动以及车辆自适应控制问题提供了有效的途径.针对上述几个方 面,对近几年国内外学者将神经网络应用到无人驾驶车辆运动控制中所取得的成果与进展进行了归纳分类,分别介绍了应用 情况并对优缺点进行评价.最后总结了神经网络在无人驾驶车辆运动控制中存在的主要问题,并展望了可能的发展方向. 关键词神经网络:非线性系统:自适应控制:稳定性:无人驾驶车辆 分类号TP183 Overview of the application of neural networks in the motion control of unmanned vehicles ZHANG Shou-wu2,WANG Heng CHEN Peng,ZHANG Xiao-yu,LI Qing 1)School of Automation and Electrical Engineering.University of Science and Technology Beijing,Beijing 100083,China 2)School of Information Science and Engineering,Beijing City University,Beijing 100083,China 3)Key Laboratory of Knowledge Automation for Industrial Processes,Ministry of Education,Beijing 100083,China Corresponding author,E-mail:liqing @ies.ustb.edu.cn ABSTRACT This paper aims to introduce the application of neural networks in the motion control of unmanned vehicles in recent years.With the breakthrough of computer,robot control,and sensing technology,the development of unmanned vehicles has entered a stage of rapid development.It can reduce driver mistakes,bring convenience to the daily travel of humans,and it is widely used in the military and dangerous fields.However,the unmanned vehicle itself has strong nonlinearity,signal delay,and parameter uncertainty and its control is affected by external factors such as the change of road adhesion coefficient and lateral wind.Therefore,traditional control methods often face challenges in controlling the vehicle stably and accurately.The learning.adaptive,and approximate nonlinear mapping abilities of neural networks provide an effective way to solve the problems of vehicle model parameter uncertainty change, external disturbance,and vehicle adaptive control.Therefore,it is increasingly applied to the motion control of unmanned vehicles.The self-learning and adaptive ability of neural networks enable them to calculate the direct output control quantity according to the state deviation of the vehicle,which can be used as the controller of the unmanned vehicle.The ability of the neural networks to approach a nonlinear mapping makes it possible to approach the unknown dynamic parts of the vehicle,such as the uncertain parameters and external disturbances,which improves the accuracy and robustness of the controller design.The neural networks can remember previous 收稿日期:2021-04-23 基金项目:国家自然科学基金资助项目(61673098.61603034):北京市自然科学基金资助项目(3182027):中央高校基本科研业务费资助项 目(FRF-GF-17-B44)神经网络在无人驾驶车辆运动控制中的应用综述 张守武1,2),王    恒1,3),陈    鹏1),张笑语1),李    擎1,3) 苣 1) 北京科技大学自动化学院,北京 100083    2) 北京城市学院信息学部,北京 100083    3) 工业过程知识自动化教育部重点实验室,北京 100083 苣通信作者, E-mail:liqing@ies.ustb.edu.cn 摘    要    无人驾驶车辆自身具有强烈的非线性、信号时延和参数不确定性,对它的控制还受到道路附着系数的变化、侧向风 等外界因素影响. 因此传统控制方法往往难以对其稳定和精确地控制. 神经网络所具有的学习能力、自适应能力和近似非线 性映射的能力,为解决车辆模型参数的不确定性、外界的扰动以及车辆自适应控制问题提供了有效的途径. 针对上述几个方 面,对近几年国内外学者将神经网络应用到无人驾驶车辆运动控制中所取得的成果与进展进行了归纳分类,分别介绍了应用 情况并对优缺点进行评价. 最后总结了神经网络在无人驾驶车辆运动控制中存在的主要问题,并展望了可能的发展方向. 关键词    神经网络;非线性系统;自适应控制;稳定性;无人驾驶车辆 分类号    TP183 Overview  of  the  application  of  neural  networks  in  the  motion  control  of  unmanned vehicles ZHANG Shou-wu1,2) ,WANG Heng1,3) ,CHEN Peng1) ,ZHANG Xiao-yu1) ,LI Qing1,3) 苣 1) School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China 2) School of Information Science and Engineering, Beijing City University, Beijing 100083, China 3) Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, Beijing 100083, China 苣 Corresponding author, E-mail: liqing@ies.ustb.edu.cn ABSTRACT    This paper aims to introduce the application of neural networks in the motion control of unmanned vehicles in recent years. With the breakthrough of computer, robot control, and sensing technology, the development of unmanned vehicles has entered a stage of rapid development. It can reduce driver mistakes, bring convenience to the daily travel of humans, and it is widely used in the military and dangerous fields. However, the unmanned vehicle itself has strong nonlinearity, signal delay, and parameter uncertainty and its control is affected by external factors such as the change of road adhesion coefficient and lateral wind. Therefore, traditional control methods  often  face  challenges  in  controlling  the  vehicle  stably  and  accurately.  The  learning,  adaptive,  and  approximate  nonlinear mapping abilities of neural networks provide an effective way to solve the problems of vehicle model parameter uncertainty change, external disturbance, and vehicle adaptive control. Therefore, it is increasingly applied to the motion control of unmanned vehicles. The self-learning and adaptive ability of neural networks enable them to calculate the direct output control quantity according to the state deviation of the vehicle, which can be used as the controller of the unmanned vehicle. The ability of the neural networks to approach a nonlinear  mapping  makes  it  possible  to  approach  the  unknown  dynamic  parts  of  the  vehicle,  such  as  the  uncertain  parameters  and external disturbances, which improves the accuracy and robustness of the controller design. The neural networks can remember previous 收稿日期: 2021−04−23 基金项目: 国家自然科学基金资助项目(61673098,61603034);北京市自然科学基金资助项目(3182027);中央高校基本科研业务费资助项 目(FRF-GF-17-B44) 工程科学学报,第 44 卷,第 2 期:235−243,2022 年 2 月 Chinese Journal of Engineering, Vol. 44, No. 2: 235−243, February 2022 https://doi.org/10.13374/j.issn2095-9389.2021.04.23.001; http://cje.ustb.edu.cn
<<向上翻页向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有