北京航空航天大学学报 ›› 2017, Vol. 43 ›› Issue (9): 1738-1745.doi: 10.13700/j.bh.1001-5965.2016.0660

• 论文 • 上一篇    下一篇

基于高斯过程的机器人自适应抓取策略

陈友东, 郭佳鑫, 陶永   

  1. 北京航空航天大学 机械工程及自动化学院, 北京 100083
  • 收稿日期:2016-08-10 出版日期:2017-09-20 发布日期:2017-02-21
  • 通讯作者: 陈友东,E-mail:chenyd@buaa.edu.cn E-mail:chenyd@buaa.edu.cn
  • 作者简介:陈友东,男,博士,副教授,硕士生导师;主要研究方向:机器人控制系统、机器人易编程;郭佳鑫,男,硕士研究生;主要研究方向:人机协作;陶永,男,博士,讲师;主要研究方向:机电一体化、智能机器人应用
  • 基金资助:
    国家“863”计划(2014AA041601);北京市科技计划(D161100003116002)

Adaptive grasping strategy of robot based on Gaussian process

CHEN Youdong, GUO Jiaxin, TAO Yong   

  1. School of Mechanical Engineering and Automation, Beijing University of Aeronautics and Astronautics, Beijing 100083, China
  • Received:2016-08-10 Online:2017-09-20 Published:2017-02-21
  • Supported by:
    National High-tech Research and Development Program of China (2014AA041601); Beijing Science and Technology Plan (D161100003116002)

摘要: 在机器人抓取作业时,目标物体的位姿经常发生变化。为了使机器人在运动过程中能够适应物体的位姿变化,提出了一种基于高斯过程的机器人自适应抓取策略。该方法建立了从观测空间到关节空间的映射,使机器人从样本中学习,省去了机器人视觉系统的标定和逆运动学求解。首先,拖动机器人抓取物体,记录物体的观测变量和机器人的关节角度;然后,利用记录的样本训练高斯过程模型,实现观测变量和关节角度的关联;最后,当得到新的观测变量时,通过训练的高斯过程模型得到机器人的关节角度。经过训练后,UR3机器人成功抓取了物体。

关键词: 高斯过程, 自适应抓取, 机器人控制, 机器人视觉, 从演示中学习

Abstract: When robot grasps an object, the pose of the object maybe change frequently. In order to make the robot adapt to the change of the pose of the object in the process of motion, an adaptive grasping strategy of robot based on Gaussian process was proposed. The proposed method maps the observation variables to the joint angles, which makes robot learn from samples and eliminates the calibration process of robot vision system and the robot inverse kinematics computation. First, the robot was dragged to grasp object. The observation variables of object and corresponding robot joint angles were recorded. Second, Gaussian process model was trained with the recorded samples, which correlates the observation variables and joint angles. Finally, after new observation variables were acquired, joint angles for grasping operation can be obtained by the trained Gaussian process model. The experiments show that UR3 robot can successfully grasp objects after training.

Key words: Gaussian process, adaptive grasping, robot control, robot vision, learning from demonstration

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发