摘要
针对抓取任务的非结构化特性,提出一种基于非规则物体三维点云的基本形体简化算法,为抓取策略的选取提供思路,提高机器人自主抓取的准确率.将不规则的复杂物体简化为由基本形体组成的简单物体,基于三维网格分割算法将物体3D数据点进行分割,依据最优拟合算法将分割后各部分拟合为球体、椭球体、圆柱体和平行六面体中的一种,实现对复杂物体的简化.实验结果表明:本文算法可应用于不同形状及姿态的非规则物体抓取,具有较高的鲁棒性.
Aiming at the unstructured features of fetching tasks,a basic form simplification algorithm based on point cloud of irregular object was proposed to describe the shapes of complex objects,thus providing ideas for the selection of grasping strategies and improving the accuracy of autonomous grasping of robots.Complex irregular objects were simplified into simple objects that composed of basic shapes. 3 D data points of object were segmented based on the three dimensional grid segmentation algorithm.Each parts of the segmented object was fitted into a sphere,ellipsoid,cylinder or parallelepiped according to the optimal fitting algorithm to realize simplification of complex object.Experimental results show that the proposed algorithm is robust and can be applied to irregular objects with different shapes and postures.
作者
曹雏清
刘汉伟
李瑞峰
CAO Chuqing;LIU Hanwei;LI Ruifeng(School of Computer and Information,Anhui Polytechnic University,Wuhu 241000,Anhui China;HIT Wuhu Robot Technology Research Institute Co.Ltd.,Wuhu 241007,Anhui China;School of Mechanical Engineering,Nanjing University of Science and Technology,Nanjing 210094,China;Robotics Institute,Harbin Insitute of Technology,Harbin 150001,China)
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2020年第1期13-19,共7页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
机器人技术与系统国家重点实验室开放研究基金资助项目(SKLRS2016KF09)
国家自然科学基金资助项目(61503186)
关键词
自主抓取
非规则物体
三维点云
基本形体简化
网格分割
最优拟合算法
autonomous grasping
irregular object
three-dimensional(3D) point cloud
basic form simplification
mesh segmentation
optimal fitting algorithm
