SIA OpenIR  > 水下机器人研究室
基于概率量度的机械臂视觉伺服目标捕获运动规划方法
Alternative TitleTarget Capture Trajectory planning for Manipulators with Visual Servos Based on Probability Measurement
祁若龙1,2; 邵健铎1; 张珂1; 唐元贵2; 赵吉宾2
Department水下机器人研究室
Source Publication吉林大学学报(工学版)
ISSN1671-5497
2020
Pages1-10
Contribution Rank1
Funding Organization中国博士后科学基金资助项目(2019M651145) ; 机器人学国家重点实验室开放基金(2019-O21)
Keyword模式识别与智能系统 视觉伺服 状态估计 不确定性 机械臂
Abstract

在机械臂视觉伺服目标捕获过程中,当机械臂存在运动噪声且其视觉传感器亦存在观测噪声时,不同抓捕轨迹会得到不同的运动精度。多源误差影响下,机械臂捕捉运动会随机地偏离预定义轨迹,存在抓取失败概率。为了对捕获成功概率进行有效评估,本文以自然界最为普遍的高斯分布描述机械臂和视觉系统的不确定性;在机械臂进行目标捕获时,首先基于快速搜索随机树 RRT生成可行捕获轨迹,用概率论结合卡尔曼滤波结合现代控制理论对其可行轨迹进行先验概率评估,将捕获概率最大的轨迹作为抓捕轨迹。首先,构建视觉伺服闭环控制系统;其次,以线性控制与卡尔曼滤波相结合,建立高斯运动系统误差模型;再次,用高斯运动模型对预规划轨迹进行迭代估计,得到单周期轨迹点的误差分布,以此定量计算机械臂到达目标区域的成功捕获概率。最后,通过仿真和试验数据的对比,验证了算法的有效性和实用性。

Other Abstract

When a manipulator captures its object with its visual servo system, if its movement system has process noise, and its visual sensors have specific observation noise, different capture trajectories will form different capture accuracy. A single trajectory of the manipulator can deviate from the predefined trajectory randomly, and have the opportunity and probability of grab failure. Feasible rapidly-exploring random tree ( RRT) capture trajectories are planned before the manipulator moves to its target. The probability theory combing with the manipulator’s linear control and Kalman filter estimation is used to evaluate the apriori probability distribution of movement error for the manipulator. Firstly, a closed loop control strategy is established by visual servo. Then, linear control method is used in combination with Kalman filter to establish error model of Gaussian motion system. After that, a predefined trajectory is assessed iteratively with the Gaussian motion model to calculate the error distributions of the entire trajectory. Through Gaussian movement prior probability estimates, the successful probability of arriving at the object region can be calculated quantificationally. At last, the effectiveness and practicability of the algorithm proposed can be verified by the comparison between simulation and experiment data.

Language中文
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/25790
Collection水下机器人研究室
Corresponding Author唐元贵
Affiliation1.沈阳建筑大学机械工程学院
2.中国科学院沈阳自动化研究所机器人学国家重点实验室
Recommended Citation
GB/T 7714
祁若龙,邵健铎,张珂,等. 基于概率量度的机械臂视觉伺服目标捕获运动规划方法[J]. 吉林大学学报(工学版),2020:1-10.
APA 祁若龙,邵健铎,张珂,唐元贵,&赵吉宾.(2020).基于概率量度的机械臂视觉伺服目标捕获运动规划方法.吉林大学学报(工学版),1-10.
MLA 祁若龙,et al."基于概率量度的机械臂视觉伺服目标捕获运动规划方法".吉林大学学报(工学版) (2020):1-10.
Files in This Item: Download All
File Name/Size DocType Version Access License
基于概率量度的机械臂视觉伺服目标捕获运动(900KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[祁若龙]'s Articles
[邵健铎]'s Articles
[张珂]'s Articles
Baidu academic
Similar articles in Baidu academic
[祁若龙]'s Articles
[邵健铎]'s Articles
[张珂]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[祁若龙]'s Articles
[邵健铎]'s Articles
[张珂]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于概率量度的机械臂视觉伺服目标捕获运动规划方法.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.