基于随机森林算法的气动软体机械臂视觉伺服
作者:
作者单位:

1.重庆大学 机械与运载工程学院,重庆 400044;2.重庆城投城市更新建设发展有限公司,重庆 400025;3.重庆工业职业技术学院,重庆 401120;4.中煤科工重庆设计研究院(集团)有限公司,重庆 400042

作者简介:

通讯作者:

中图分类号:

TP241.3

基金项目:

中央高校基本科研业务费科研平台与成果培育专项(2020CDCGJX023)


Visual Servo Control of Pneumatic Soft Manipulator Based on Random Forest Regression Algorithm
Author:
Affiliation:

1.College of Mechanical Engineering, Chongqing University, Chongqing 400044, P.R.China;2.Chongqing City Construction Development Co., Ltd, Chongqing 400025, P.R.China;3.Chongqing Industry Polytechnic College, Chongqing 401120, P.R.China;4.CCTEG Chongqing Research Institute, Chongqing 400042, P.R.China

Fund Project:

Supported by the Fundamental Research Funds for the Central Universities(2020CDCGJX023)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    软体机械臂具有灵活性和柔顺性的特点,可在实现对位姿跟踪的同时确保与环境交互的安全性,近年成为研究的热点。但由于软体机械臂材料变形是非线性的,其运动学建模的参数众多且难以获得准确值,使软体机械臂实现运动学控制较为困难。为了补偿软体机械臂的不确定性,在现在视觉伺服的基础上,提出一种基于历史数据驱动的手眼视觉伺服新方法。该方法结合基于随机森林算法的控制器来完成机械臂控制任务,通过对历史数据聚类,基于随机森林回归模型建立软体机械臂驱动状态和末端图像特征的逆映射,无需求解机械臂和摄像机的任何参数,即可快速获取系统输入变量。实验结果表明,所提出的方法可以较好地实现预期控制目标。

    Abstract:

    The soft manipulator has the characteristics of dexterity and flexibility, which can ensure the safety of interaction with the environment while tracking the position and posture. It has become a research highlight in recent years. However, because the material deformation of the soft manipulator is nonlinear, its kinematic modeling parameters are numerous and it is difficult to obtain accurate values, which makes it difficult to realize the kinematic control of the soft manipulator. In order to compensate for the uncertainty of the soft manipulator, based on the current visual servoing, a new hand-eye visual servoing method driven by historical data is proposed. This method combines the controller based on the random forest algorithm to complete the control task of the manipulator. By clustering historical data, the inverse mapping of the driving state of the soft manipulator and image characteristics is established based on the random forest regression model. The system input variables are predicted quickly without solving any parameters of the manipulator and camera. The experimental results show that the proposed method can better achieve the expected control objectives.

    参考文献
    相似文献
    引证文献
引用本文
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-12-10
  • 最后修改日期:2022-02-19
  • 录用日期:2022-02-21
  • 在线发布日期:
  • 出版日期: