车辆车道保持系统人机共享转向控制  

Human-Machine Shared Steering Control for Vehicle Lane Keeping Systems

作　　者：李凯 韩增文 陈金建 李斌 王洪波 LI Kai;HAN Zengwen;CHEN Jinjian;LI Bin;WANG Hongbo(Guangdong Airport Authority Co.,Ltd.,Guangzhou Guangdong 510000,China;HIT Robot Group(Zhongshan)Institute of Unmanned Equipment and Artificial Intelligence,Zhongshan Guangdong 528400,China)

机构地区：[1]广东省机场管理集团有限公司,广东广州510440 [2]哈工大机器人(中山)无人装备与人工智能研究院,广东中山528400

出　　处：《交通节能与环保》2024年第4期104-110,共7页Transport Energy Conservation & Environmental Protection

基　　金：广东省重点领域研发计划项目(2020B0101130024)。

摘　　要：基于神经网络时滞的人机共享控制方法可有效提高车辆车道保持系统的性能。为了捕捉系统的非线性和不确定性特征,如非线性转向、变化的速度和转向行为的不确定性,采用了T-S模糊方法对驾驶员-车辆系统进行建模。在系统建模之后,考虑采用基于神经网络时滞的控制结构,并基于一定时滞相关的矩阵不等式的可行性设计时滞相关的状态反馈控制器。基于李亚普诺夫泛函理论,给出了计算期望的人机共享转向控制器的一组充分条件,并在Matlab/Simulink仿真平台上进行了仿真测试,结果表明该方法能显著提高车道保持能力和驾驶员操纵舒适性方面。A neural network time-delay based human-machine shared control approach can effectively improve the performance of the vehicle lane keeping system.To capture the nonlinear and uncertain features of the system,such as nonlinear steering,varying speeds,and uncertainty in steering behavior,a T-S fuzzy approach is used to model the driver-vehicle system.After modeling the system,a neural network-delay based control structure is considered,and a time delay related state feedback controller is designed based on the feasibility of certain time delay related matrix inequalities.A set of sufficient conditions to compute the desired human-machine shared steering controller is given based on Lyapunov function theory.Finally,the simulation test is carried out on the Matlab/Simulink simulation platform,and the results show that the method provides a significant improvement in lane keeping ability and driver maneuvering comfort.

关 键 词：车辆系统动力学 人机共享控制 模糊模型 时滞 

分 类 号：U461[机械工程—车辆工程]