Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning
Finding feasible motion for robots with high-dimensional configuration space is a fundamental problem in robotics. Sampling-based motion planning algorithms have been shown to be effective for these high-dimensional systems. However, robots are often subject to task constraints (e.g., keeping a glas...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-12-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/7/12/395 |
id |
doaj-e3a336170aed4f56a2dd7c3d81896abb |
---|---|
record_format |
Article |
spelling |
doaj-e3a336170aed4f56a2dd7c3d81896abb2020-11-24T23:57:11ZengMDPI AGElectronics2079-92922018-12-0171239510.3390/electronics7120395electronics7120395Learning the Metric of Task Constraint Manifolds for Constrained Motion PlanningFusheng Zha0Yizhou Liu1Wei Guo2Pengfei Wang3Mantian Li4Xin Wang5Jingxuan Li6State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, ChinaState Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, ChinaState Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, ChinaState Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, ChinaState Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, ChinaShenzhen Academy of Aerospace Technology, Shenzhen 518000, ChinaState Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, ChinaFinding feasible motion for robots with high-dimensional configuration space is a fundamental problem in robotics. Sampling-based motion planning algorithms have been shown to be effective for these high-dimensional systems. However, robots are often subject to task constraints (e.g., keeping a glass of water upright, opening doors and coordinating operation with dual manipulators), which introduce significant challenges to sampling-based motion planners. In this work, we introduce a method to establish approximate model for constraint manifolds, and to compute an approximate metric for constraint manifolds. The manifold metric is combined with motion planning methods based on projection operations, which greatly improves the efficiency and success rate of motion planning tasks under constraints. The proposed method Approximate Graph-based Constrained Bi-direction Rapidly Exploring Tree (AG-CBiRRT), which improves upon CBiRRT, and CBiRRT were tested on several task constraints, highlighting the benefits of our approach for constrained motion planning tasks.https://www.mdpi.com/2079-9292/7/12/395motion planningconstraint manifoldsapproximate metricprojection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fusheng Zha Yizhou Liu Wei Guo Pengfei Wang Mantian Li Xin Wang Jingxuan Li |
spellingShingle |
Fusheng Zha Yizhou Liu Wei Guo Pengfei Wang Mantian Li Xin Wang Jingxuan Li Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning Electronics motion planning constraint manifolds approximate metric projection |
author_facet |
Fusheng Zha Yizhou Liu Wei Guo Pengfei Wang Mantian Li Xin Wang Jingxuan Li |
author_sort |
Fusheng Zha |
title |
Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning |
title_short |
Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning |
title_full |
Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning |
title_fullStr |
Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning |
title_full_unstemmed |
Learning the Metric of Task Constraint Manifolds for Constrained Motion Planning |
title_sort |
learning the metric of task constraint manifolds for constrained motion planning |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2018-12-01 |
description |
Finding feasible motion for robots with high-dimensional configuration space is a fundamental problem in robotics. Sampling-based motion planning algorithms have been shown to be effective for these high-dimensional systems. However, robots are often subject to task constraints (e.g., keeping a glass of water upright, opening doors and coordinating operation with dual manipulators), which introduce significant challenges to sampling-based motion planners. In this work, we introduce a method to establish approximate model for constraint manifolds, and to compute an approximate metric for constraint manifolds. The manifold metric is combined with motion planning methods based on projection operations, which greatly improves the efficiency and success rate of motion planning tasks under constraints. The proposed method Approximate Graph-based Constrained Bi-direction Rapidly Exploring Tree (AG-CBiRRT), which improves upon CBiRRT, and CBiRRT were tested on several task constraints, highlighting the benefits of our approach for constrained motion planning tasks. |
topic |
motion planning constraint manifolds approximate metric projection |
url |
https://www.mdpi.com/2079-9292/7/12/395 |
work_keys_str_mv |
AT fushengzha learningthemetricoftaskconstraintmanifoldsforconstrainedmotionplanning AT yizhouliu learningthemetricoftaskconstraintmanifoldsforconstrainedmotionplanning AT weiguo learningthemetricoftaskconstraintmanifoldsforconstrainedmotionplanning AT pengfeiwang learningthemetricoftaskconstraintmanifoldsforconstrainedmotionplanning AT mantianli learningthemetricoftaskconstraintmanifoldsforconstrainedmotionplanning AT xinwang learningthemetricoftaskconstraintmanifoldsforconstrainedmotionplanning AT jingxuanli learningthemetricoftaskconstraintmanifoldsforconstrainedmotionplanning |
_version_ |
1725455214984560640 |