arrow
返回

Object Pose Estimation in Accommodation Space using an Improved Fruit Fly Optimization Algorithm

delete2018-10-25
delete5
PRE
AI
Q
Qingda Guo *
Y
Yanming Quan
C
Changcheng Jiang
DOI:10.1007/s10846-018-0940-3delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
The accommodation space changes as flexible products are packed into it. In order to improve the automatic loading of containers, it is necessary to solve the problem of object pose estimation in accommodation space. The goal of this study is to establish a method for pose estimation of a target object in the accommodation space. Firstly, the paper introduces basic algorithms and concepts, including the quick hull (Qhull) algorithm, oriented bounding box (OBB) algorithm, and fruit fly optimization algorithm (FOA). Secondly, the constraint conditions and the objective function of pose estimation are set up according to the pose variables in three-dimensional (3D) space, and a solution method for pose estimation is established using an improved FOA. Then, the algorithms with different population parameters are simulated, and the optimal parameters are obtained. The bounding box algorithm is used for system optimization, whereas a convex hull is used to simplify the target object significantly, reducing the corresponding running time. Finally, the hardware platform of the industrial robot is established, the initial and final poses of the end-effector are obtained using the proposed method, and tests are performed for different cases. The results show that the application of convex hull algorithm can significantly simplify a target object reducing the running time, and half individuals of the population guide the entire population to search for an optimal pose (6 degrees of freedom) in accommodation space.
Keyword:
Pose estimation
Fruit fly optimization algorithm
Quick hull
Oriented Bounding Box
Accommodation space
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

J
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
IF:
2.8
论文数:
3.9K
被引数:
6.9K

机构

S
south china university of technology
学者数:
6.8W
论文数: 5.1W
被引数: 85
引用论文

引用论文

err分享
err收藏
A novel hybrid tabu search approach to container loading
err2011-04-01
err53
PREAI
errLiu, Jiamin; Yue, Yong; Dong, Zongran; Maple, Carsten; Keech, Malcolm
err分享
err收藏
err分享
err收藏
没有更多内容