移动机器人RBF神经网络自适应PD跟踪控制  

RBF Neural Network Adaptive PD Tracking Control of Mobile Robot

作　　者：马东[1,2] 董力元 王立玲 刘秀玲[1,2] 王洪瑞 MA Dong;DONG Li-yuan;WANG Li-ling;LIU Xiu-ling;WANG Hong-rui(College of Electronic Information Engineering,Hebei University,Baoding 071002,China;Key Laboratory of Digital Medical Engineering of Hebei Province,Baoding 071002,China)

机构地区：[1]河北大学电子信息工程学院,河北保定071002 [2]河北省数字医疗工程重点实验室,河北保定071002

出　　处：《控制工程》2020年第12期2092-2098,共7页Control Engineering of China

基　　金：国家自然科学基金项目(61673158)。

摘　　要：针对轮子打滑条件下的轮式移动机器人,提出了一种基于径向基函数(Radical BasisFunction,RBF)神经网络自适应的比例微分(ProportionalDifferential,PD)跟踪控制策略。首先,建立了轮式移动机器人在打滑条件下的动力学模型。其次,利用反步法设计运动学控制器,基于动力学模型设计PD控制器,采用带有参数自适应的RBF神经网络对打滑下的动力学模型中的参数和非参数不确定性进行了前馈补偿,并利用Lyapunov稳定性理论证明了闭环系统稳定性。最后,对本文提出的控制方法进行了仿真对比实验。实验结果表明,该控制方法能够较好补偿机器人轮子打滑下的不确定性影响,提高了轮式移动机器人轨迹跟踪的鲁棒性。Aiming at the wheeled mobile robots(WMR)under wheel slip conditions,an adaptive proportional differential(PD)tracking control strategy based on radical basis function(RBF)neural network is proposed.Firstly,the dynamic model of the wheeled mobile robot under sliding conditions is established.Secondly,the kinematic controller is designed by the backstepping method,and the PD controller is designed based on the dynamic model.The RBF neural network with adaptive parameters is used to make feedforward compensation for the parametric and non-parametric uncertainties in the dynamic model of slippage.Then the stability of the closed-loop system is proved by Lyapunov stability theory.Finally,a simulation and comparison experiment is carried out on the control method proposed in this paper.The results show that the control method can better compensate the uncertainty of the robot’s wheel slip and improve the robustness of the wheeled mobile robot’s trajectory tracking.

关 键 词：移动机器人 轨迹跟踪 轮子打滑 RBF神经网络 自适应控制 PD控制 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]