系统仿真学报 ›› 2017, Vol. 29 ›› Issue (8): 1845-1850.doi: 10.16182/j.issn1004731x.joss.201708027

• 仿真应用工程 • 上一篇    下一篇

基于回声状态网络的机械臂的视觉伺服控制

李国友, 苏侠飞, 秦晓磊, 史香雪   

  1. 燕山大学工业计算机控制工程河北省重点实验室,秦皇岛 066004
  • 收稿日期:2015-09-09 发布日期:2020-06-01
  • 作者简介:李国友(1972-),男,河北秦皇岛,博士,教授,研究方向为伺服控制、智能控制;苏侠飞(通讯作者1989-),女,河北邯郸,硕士生,研究方向为伺服控制、智能控制。
  • 基金资助:
    河北省自然科学基金(F2012203111),河北省高等学校科学技术研究青年基金(2011139)

Robotic Manipulator's Visual Servo Control Based on Echo State Networks

Li Guoyou, Su Xiafei, Qin Xiaolei, Shi Xiangxue   

  1. Key Laboratory of Industrial Computer Control Engineering of Yanshan University, Qinhuangdao 066004, China
  • Received:2015-09-09 Published:2020-06-01

摘要: 由于机械臂本身的非线性和强耦合性,使得在研究机械臂控制问题的时候不得不考虑由此而带来的模型不确定项的问题。针对机械臂系统模型中的不确定项部分,将回声状态网络引入到机械臂的视觉伺服控制系统中。利用回声状态网络对系统的不确定项部分进行辨识,从而在控制律中实现对该部分的补偿,最终实现机械臂的定位控制。利用MATLAB仿真软件对系统进行仿真,仿真结果与没有使用回声状态网络的系统进行比较。结果表明,回声状态网络能很好地对系统的不确定项进行辨识,并通过对不确定项的补偿,使系统能更快达到期望要求。

关键词: 回声状态网络, 视觉伺服, 机械臂, MATLAB仿真

Abstract: The inaccuracy in robotic manipulator modeling, which due to the nonlinear and strong coupling of robotic manipulator itself, cannot be ignored on the study of the robotic manipulator control problem. Aiming at the inaccuracy in robotic manipulator modeling, this study led echo state network in the visual servo control system of robotic manipulator. In order to achieve the robotic manipulator positioning control, this study used the echo state network to identify inaccurate item and compensates the uncertainties of the model in the control law. The simulation model of the simulated system was built with MATLAB simulation software. The results, compared with the visual servo system without echo state network, the echo state network can well identify the inaccuracy in robotic manipulator modeling. The system can quickly achieve the desired requirements with compensate the uncertainties of the model.

Key words: echo state network, visual servo, robotic manipulator, MATLAB simulation

中图分类号: