ETRI-Knowledge Sharing Plaform

ENGLISH
논문 검색
Type SCI
Year ~ Keyword

Detail

Journal Article Multi-Tree-Based Path Planning of Robotic Manipulators for Unstructured Depalletizing Tasks
Cited 2 time in scopus Download 18 time Share share facebook twitter linkedin kakaostory
Authors
Donghyung Kim, Song Byoung Youl, Kim Joong Bae
Issue Date
202004
Source
제어로봇시스템학회논문지, v.26 no.4, pp.263-268
ISSN
1976-5622
Publisher
제어로봇시스템학회
DOI
https://dx.doi.org/10.5302/J.ICROS.2020.19.0160
Project Code
19HS1900, Development of Core Technology of Robot Task-Intelligence for Improvement of Labor Condition, Wonpil Yu
Abstract
This paper presents an algorithm for robot path planning for unstructured depalletizing tasks. Parcel depalletization is a multi-start single-goal path planning problem that involves placing multiple parcels in the same location. To solve this problem, we propose a new path planning algorithm called the multi-start single-goal RRT (Rapidly-exploring Random Tree), which is an extended version of the bidirectional RRT. The multi-start single-goal RRT is based on multi-RRT and uses multiple trees to find a path that connects multiple parcels to a single placing position. We verified the performance of the proposed algorithm by solving the three-dimensional path planning problem with a simulation before applying it to articulated robot arms.
KSP Keywords
Multi-start, Path planning algorithm, Path planning problem, Rapidly-exploring random tree(RRT), Robot path planning, Three dimensional(3D), Three-Dimensional Path planning