改进的GA与BP-PID融合移动机器人轨迹跟踪研究  

Mobile robot trajectory tracking based on improved GA and BP-PID

作　　者：石秀敏[1] 孙建康 邓三鹏[1] SHI Xiumin;SUN Jiankang;DENG Sanpeng(Institute of Robotics and Intelligent Equipment,Tianjin University of Technology and Education,Tianjin 300222,China)

机构地区：[1]天津职业技术师范大学机器人及智能装备研究院,天津300222

出　　处：《天津职业技术师范大学学报》2022年第1期20-25,共6页Journal of Tianjin University of Technology and Education

基　　金：天津市科技重大专项(18ZXJMTG00160).

摘　　要：针对PID控制器轨迹跟踪精度差的问题,在BP网络对PID参数拟合的基础上,利用算法融合的思想,使用改进后的遗传算法对BP网络进行参数寻优,避免BP网络陷入局部最优解,再使用BP网络对PID参数进行拟合。文章给出了控制算法的整体流程,并结合移动机器人的运动学方程进行了仿真对比实验。结果显示:改进后的融合算法相比PID算法控制误差更小,即改进的GA与BP-PID融合算法在移动机器人轨迹跟踪精度上发生了明显的改善。The PID controller has poor accuracy in trajectory tracking.To address this problem,the study uses algorithm fusion based on the BP network fitting PID parameters.The improved genetic algorithm optimizes the parameters of the BP network preventing it from falling into the local optimal area.Then the BP network is used to fit the PID parameters.This paper gives the overall flow of the control algorithm and conducts a simulation comparison experiment with the kinematics equation of the mobile robot.The results show that the improved fusion algorithm has a smaller control error than the PID algorithm.That is,the improved GA and BP-PID fusion algorithm has significantly improved the trajectory tracking accuracy of the mobile robot.

关 键 词：移动机器人 遗传算法 BP神经网络 PID轨迹跟踪 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]