基于卷积神经网络的机械臂目标轨迹跟踪控制方法研究  

Research on Target Trajectory Tracking Control Method for Robotic Arms Based onConvolutional Neural Networks

在线阅读下载全文

作  者:丁戈 李松 付国萍 韩晓翔 王正武 DING Ge;LI Song;FU Guoping;HAN Xiaoxiang;WANG Zhengwu(Ultra High Voltage Branch,State Grid Xinjiang Electric Power Co.,Ltd.,Urumqi 830063,China)

机构地区:[1]国网新疆电力有限公司超高压分公司,新疆乌鲁木齐830063

出  处:《机械与电子》2024年第11期53-57,共5页Machinery & Electronics

基  金:新疆电力有限公司科技项目(5230CD230001)。

摘  要:机械臂通常在复杂的环境中运作,考虑到工作空间限制、载荷扰动和安全性等要求,使得传统的机械臂目标轨迹跟踪控制中存在位姿误差较大的问题。为此,提出基于卷积神经网络的机械臂目标轨迹跟踪控制方法。确定机械臂系统的总不确定项,获取机械臂系统在名义模型下的控制律,利用自适应径向基函数(RBF)卷积神经网络计算总不确定项的预估误差,补偿机械臂系统的不确定项;分析机械臂末端执行器位置与速度的状态,利用伪逆算法计算期望关节速度的最优解建立目标轨迹控制系统方程,获得最终的机械臂目标轨迹跟踪控制律,完成跟踪控制。实验结果表明,所提方法位姿跟踪精度更高、适应性更强且跟踪速度更快。The manipulator usually operates in a complex environment.Considering the requirements of working space limitation,load disturbance and safety,the traditional manipulator target trajectory tracking control has a large pose error.Therefore,a convolutional neural network based tracking control method for robot arm is proposed.The total uncertainty of the manipulator system is determined,the control law of the manipulator system under the nominal model is obtained,and the adaptive Radial Basis Function convolutional neural network is used to calculate the prediction error of the total uncertainty,and compensate the uncertainty of the manipulator system;the position and velocity of the end-effector of the manipulator are analyzed,and the optimal solution of the desired joint velocity is calculated by using the pseudo-inverse algorithm to establish the target trajectory control system equation,and the final control law of the robot’s target trajectory tracking is obtained to complete the tracking control.The experimental results show that the proposed method has higher precision,better adaptability and faster tracking speed.

关 键 词:机械臂目标轨迹 自适应RBF卷积神经网络 控制律 伪逆算法 跟踪误差 

分 类 号:TP242[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象