采用改进神经网络PID控制的移动机器人轨迹追踪控制研究
|
摘要
为了提高双轮移动机器人运动轨迹追踪精度,采用改进粒子群算法优化BP神经网络PID控制器,并对控制效果进行仿真验证。创建双轮移动机器人模型简图,给出运动轨迹误差方程式。在传统PID控制基础上增加BP神经网络结构,引用粒子群算法并对其进行改进,采用改进粒子群算法优化BP神经网络PID控制调整参数,给出双轮移动机器人PID控制参数优化流程。采用数学软件MATLAB对双轮移动机器人轨迹追踪误差进行仿真验证,并与传统PID控制追踪误差进行对比。仿真曲线显示:在理想环境中,双轮移动机器人采用两种控制方法都能较好地实现轨迹追踪,追踪误差较小;在干扰波形环境中,传统PID控制双轮移动机器人追踪误差较大,而改进PID控制双轮移动机器人追踪误差较小。采用改进粒子群算法优化BP神经网络PID控制器,可以提高移动机器人运动轨迹追踪精度。
In order to improve the tracking accuracy of two-wheeled mobile robot, the improved particle swarm optimization algorithm is used to optimize the BP neural network PID controller, and the control effect is verified by simulation. The model of two wheeled mobile robot is created and the error equation of motion trajectory is given. The structure of BP neural network is added to the traditional PID control, and the particle swarm algorithm is used to improve it. The improved particle swarm algorithm is used to optimize the PID control parameters of BP neural network, and the PID control parameters optimization process of two-wheeled mobile robot is given.The trajectory tracking error of two-wheeled mobile robot is simulated and verified by MATLAB, and compared with the traditional PID control tracking error. Simulation curves show that in ideal environment, two-wheeled mobile crobots can achieve better trajectory tracking with less tracking error. In disturbance waveform environment, the tracking error of traditional PID control two-wheeled mobile robots is larger, while which of the improved PID control two-wheeled mobile robots is smaller. The improved particle swarm optimization algorithm is used to optimize BP neural network PID controller, which can improve the tracking accuracy of mobile robot.
In order to improve the tracking accuracy of two-wheeled mobile robot, the improved particle swarm optimization algorithm is used to optimize the BP neural network PID controller, and the control effect is verified by simulation. The model of two wheeled mobile robot is created and the error equation of motion trajectory is given. The structure of BP neural network is added to the traditional PID control, and the particle swarm algorithm is used to improve it. The improved particle swarm algorithm is used to optimize the PID control parameters of BP neural network, and the PID control parameters optimization process of two-wheeled mobile robot is given.The trajectory tracking error of two-wheeled mobile robot is simulated and verified by MATLAB, and compared with the traditional PID control tracking error. Simulation curves show that in ideal environment, two-wheeled mobile crobots can achieve better trajectory tracking with less tracking error. In disturbance waveform environment, the tracking error of traditional PID control two-wheeled mobile robots is larger, while which of the improved PID control two-wheeled mobile robots is smaller. The improved particle swarm optimization algorithm is used to optimize BP neural network PID controller, which can improve the tracking accuracy of mobile robot.
引文
[1]李睿敏.面向分气管焊接的桁架机器人轨迹控制研究与系统开发[D].厦门:厦门大学,2017.
[2]徐成宇,高洪.基于关节空间与工作空间协同的6R点焊机器人路径规划方法[J].井冈山大学学报:自然科学版,2017,38(5):59-62.
[3]楼巍,陈磊,严利民.基于模糊辨识的移动机器人轨迹控制算法的研究[J].仪表技术,2013(1):18-20.
[4]马玲,牟彬瑞.移动机器人运动轨迹控制算法研究[J].工业仪表与自动化装置,2018(4):132-135.
[5]李逃昌.农业轮式移动机器人自适应滑模路径跟踪控制[J].中国机械工程,2018,29(5):579-584.
[6]李保国,张春喜.双轮移动机器人安全目标追踪与自动避障算法[J].控制理论与应用,2007,24(4):535-539.
[7]Zhong J,Fan J Z,Zhu Y H,et al.One Nonlinear PIDControl to Improve the Control Performance of a Manipulator Actuated by a Pneumatic Muscle Actuator[J].Advances in Mechanical Engineering,2014,125(5):369-378.
[8]曹平军,曲林伟,王强,等.某驱动步进电动机增量PID控制研究[J].舰船电子工程,2017,37(8):162-163.
[9]杨杰群.基于BP神经网络的情感机器人玩具的设计与实现[D].广州:华南理工大学,2014.
[10]Agand P,Shoorehdeli M A,Khaki-Sedigh A.Adaptive recurrent neural network with Lyapunov stability learning rules for robot dynamic terms identification[J].Engineer-ing Applications of Artificial Intelligence,2017,65(10):2-9.
[11]刘衍民.粒子群算法的研究及应用[D].济南:山东师范大学,2011.
[12]张迅,王平,邢建春,等.基于高斯函数递减惯性权重的粒子群优化算法[J].计算机应用研究,2012,29(10):3710-3713.
[2]徐成宇,高洪.基于关节空间与工作空间协同的6R点焊机器人路径规划方法[J].井冈山大学学报:自然科学版,2017,38(5):59-62.
[3]楼巍,陈磊,严利民.基于模糊辨识的移动机器人轨迹控制算法的研究[J].仪表技术,2013(1):18-20.
[4]马玲,牟彬瑞.移动机器人运动轨迹控制算法研究[J].工业仪表与自动化装置,2018(4):132-135.
[5]李逃昌.农业轮式移动机器人自适应滑模路径跟踪控制[J].中国机械工程,2018,29(5):579-584.
[6]李保国,张春喜.双轮移动机器人安全目标追踪与自动避障算法[J].控制理论与应用,2007,24(4):535-539.
[7]Zhong J,Fan J Z,Zhu Y H,et al.One Nonlinear PIDControl to Improve the Control Performance of a Manipulator Actuated by a Pneumatic Muscle Actuator[J].Advances in Mechanical Engineering,2014,125(5):369-378.
[8]曹平军,曲林伟,王强,等.某驱动步进电动机增量PID控制研究[J].舰船电子工程,2017,37(8):162-163.
[9]杨杰群.基于BP神经网络的情感机器人玩具的设计与实现[D].广州:华南理工大学,2014.
[10]Agand P,Shoorehdeli M A,Khaki-Sedigh A.Adaptive recurrent neural network with Lyapunov stability learning rules for robot dynamic terms identification[J].Engineer-ing Applications of Artificial Intelligence,2017,65(10):2-9.
[11]刘衍民.粒子群算法的研究及应用[D].济南:山东师范大学,2011.
[12]张迅,王平,邢建春,等.基于高斯函数递减惯性权重的粒子群优化算法[J].计算机应用研究,2012,29(10):3710-3713.