A vision-guided multi-robot cooperation framework for learning-by-demonstration and task reproduction
File(s)
Accepted version
Author(s)
Huang, B
Ye, M
Lee, S
Yang, GZ
Type
Conference Paper
Abstract
This paper presents a multi-robot system for manufacturing
personalized medical stent graft. The proposed system is a modularized
system with three major components: a (personalized) mandrel module,
a bimanual sewing module and a vision module. The mandrel module in-
corporates the personalization of the product, while the bimanual sewing
module adopts a learning-by-demonstration approach to transfer human
hand sewing skills to the robots. The human demonstrations were firstly
observed by the vision module, and then encoded using a statistical
model to generate the reference motion trajectory. During autonomous
robot sewing, the vision module plays the role of coordinating multi-
robot collaboration. Experiment results show that the robots can sew
with sub-millimeter accuracy and adapt to multiple personalized stent
designs. The proposed system is generalizable to other manipulation
tasks, especially for mass production of customized products and where
bimanual or multi-robot cooperation is required.
personalized medical stent graft. The proposed system is a modularized
system with three major components: a (personalized) mandrel module,
a bimanual sewing module and a vision module. The mandrel module in-
corporates the personalization of the product, while the bimanual sewing
module adopts a learning-by-demonstration approach to transfer human
hand sewing skills to the robots. The human demonstrations were firstly
observed by the vision module, and then encoded using a statistical
model to generate the reference motion trajectory. During autonomous
robot sewing, the vision module plays the role of coordinating multi-
robot collaboration. Experiment results show that the robots can sew
with sub-millimeter accuracy and adapt to multiple personalized stent
designs. The proposed system is generalizable to other manipulation
tasks, especially for mass production of customized products and where
bimanual or multi-robot cooperation is required.
Date Issued
2017-12-14
Date Acceptance
2017-06-14
Citation
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp.4797-4804
Publisher
IEEE
Start Page
4797
End Page
4804
Journal / Book Title
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Copyright Statement
© 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor
Engineering & Physical Science Research Council (EPSRC)
Grant Number
EP/L020688/1
Source
IEEE/RSJ International Conference on Intelligent Robots and Systems
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science, Information Systems
Robotics
Computer Science
ROBOT
Publication Status
Published
Start Date
2017-09-24
Finish Date
2017-09-28
Coverage Spatial
Vancouver, Canada
Date Publish Online
2017-12-14