Transferring visuomotor learning from simulation to the real world for robotics manipulation tasks

File Description SizeFormat 
iros2018-learning-visual-stamped.pdfAccepted version4.25 MBAdobe PDFView/Open
Title: Transferring visuomotor learning from simulation to the real world for robotics manipulation tasks
Authors: Nguyen, P
Fischer, T
Chang, HJ
Pattacini, U
Metta, G
Demiris, Y
Item Type: Conference Paper
Abstract: Hand-eye coordination is a requirement for many manipulation tasks including grasping and reaching. However, accurate hand-eye coordination has shown to be especially difficult to achieve in complex robots like the iCub humanoid. In this work, we solve the hand-eye coordination task using a visuomotor deep neural network predictor that estimates the arm's joint configuration given a stereo image pair of the arm and the underlying head configuration. As there are various unavoidable sources of sensing error on the physical robot, we train the predictor on images obtained from simulation. The images from simulation were modified to look realistic using an image-to-image translation approach. In various experiments, we first show that the visuomotor predictor provides accurate joint estimates of the iCub's hand in simulation. We then show that the predictor can be used to obtain the systematic error of the robot's joint measurements on the physical iCub robot. We demonstrate that a calibrator can be designed to automatically compensate this error. Finally, we validate that this enables accurate reaching of objects while circumventing manual fine-calibration of the robot.
Issue Date: 7-Jan-2019
Date of Acceptance: 29-Jun-2018
URI: http://hdl.handle.net/10044/1/62214
DOI: 10.1109/IROS.2018.8594519
ISBN: 9781538680940
ISSN: 2153-0866
Publisher: IEEE
Start Page: 6667
End Page: 6674
Copyright Statement: © 2018 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.
Conference Name: IEEE/RSJ International Conference on Intelligent Robots and Systems
Publication Status: Published
Start Date: 2018-10-01
Finish Date: 2018-10-05
Conference Place: Madrid, Spain
Online Publication Date: 2019-01-07
Appears in Collections:Faculty of Engineering
Electrical and Electronic Engineering



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx