| 286 | 2 | 15 |
| 下载次数 | 被引频次 | 阅读次数 |
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。
Abstract：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.
[1]张施皛，唐天宇，张志明，等.基于CNN-PID的竞赛机器人赛道识别与自主驾驶[J].实验技术与管理，2020,37(9):39-43,48.
[2]刘碧飞，刘泓滨，李华文.全向移动机器人自适应滑模轨迹跟踪控制[J].农业装备与车辆工程，2020,58(12):65-69,84.
[3]WANG C C,LIU X F,YANG X Q,et al.Trajectory tracking of an omni-directional wheeled mobile robot using a model predictive control strategy[J].Applied Sciences,2018,8(2):231.
[4]CALZOLARI D,SCHüRMANN B,ALTHOFF M.Comparison of trajectory tracking controllers for autonomous vehicles[C]//2017 IEEE 20th International Conference on Intelligent Transportation Systems(ITSC).Yokohama:IEEE,2017:1-8.
[5]BARUA R,MANDAL S,MANDAL S.Motion analysis of a mobile robot with three omni-directional wheels[J].International Journal of Innovative Science,Engineering and Technology,2015,2:644-648.
[6]SANTOS J,CONCEI??O A G S,SANTOS T L M.Trajectory tracking of omni-directional mobile robots via predictive control plus a filtered Smith predictor[J].IFAC-Papers On Line,2017,50(1):10250-10255.
[7]贾松敏，卢兴阳，张祥银，等.轮子打滑状态下全向移动机器人轨迹跟踪控制[J].控制与决策，2020,35(4):833-842.
[8]赵涛，王屹华.轮式移动机器人全局轨迹跟踪控制[J].微电机，2020,53(1):106-107,111.
[9]严友，李美.农用车辆单神经元自适应PID轨迹跟踪控制[J].机械设计与制造，2020(10):228-231,235.
[10]王锐.全向移动康复训练机器人三维建模与控制方法研究[D].沈阳：沈阳工业大学，2018.
[11]叶长龙，张思阳，于苏洋，等.基于神经网络的全方位移动机器人运动稳定性研究[J].机器人，2019,41(4):443-451.
[12]ZHAO B,WANG H,LI Q,et al.PID trajectory tracking control of autonomous ground vehicle based on genetic algorithm[C]//2019 Chinese Control and Decision Conference(CCDC).Nanchang:IEEE,2019:3677-3682.
[13]王福忠，任吉利，刘薇.基于遗传算法优化BP网络的箱式变电站故障预测策略[J].河南理工大学学报（自然科学版），2019,38(5):93-98.
[14]王其兵.全向轮式移动机器人轨迹跟踪控制研究[D].沈阳：东北大学，2011.
基本信息:
DOI：10.19573/j.issn2095-0926.202201004
中图分类号:TP242;TP18
引用信息:
[1]石秀敏,孙建康,邓三鹏.改进的GA与BP-PID融合移动机器人轨迹跟踪研究[J].天津职业技术师范大学学报,2022,32(01):20-25.DOI:10.19573/j.issn2095-0926.202201004.
基金信息:
天津市科技重大专项（18ZXJMTG00160）