Guided Learning from Demonstration for Robust Transferability

Sukkar, F; Moreno, VH; Vidal-Calleja, T; Deuse, J

Guided Learning from Demonstration for Robust Transferability

Sukkar, F Moreno, VH Vidal-Calleja, T Deuse, J

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023, 2023-May, pp. 5048-5054
Issue Date:: 2023-07-04

Embargoed

	Filename	Description	Size
	ICRA_23___Guided_learning_from_demonstration_for_robust_transferability.pdf	Accepted version	5.45 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 4 Jul 2025

Full metadata record

Field	Value	Language
dc.contributor.author	Sukkar, F
dc.contributor.author	Moreno, VH
dc.contributor.author	Vidal-Calleja, T
dc.contributor.author	Deuse, J
dc.date	2023-05-29
dc.date.accessioned	2023-10-28T01:58:42Z
dc.date.available	2023-10-28T01:58:42Z
dc.date.issued	2023-07-04
dc.identifier.citation	2023 IEEE International Conference on Robotics and Automation (ICRA), 2023, 2023-May, pp. 5048-5054
dc.identifier.isbn	9798350323658
dc.identifier.issn	1050-4729
dc.identifier.uri	http://hdl.handle.net/10453/172875
dc.description.abstract	Learning from demonstration LfD has the potential to greatly increase the applicability of robotic manipulators in modern industrial applications Recent progress in LfD methods have put more emphasis in learning robustness than in guiding the demonstration itself in order to improve robustness The latter is particularly important to consider when the target system reproducing the motion is structurally different to the demonstration system as some demonstrated motions may not be reproducible In light of this this paper introduces a new guided learning from demonstration paradigm where an interactive graphical user interface GUI guides the user during demonstration preventing them from demonstrating non reproducible motions The key aspect of our approach is determining the space of reproducible motions based on a motion planning framework which finds regions in the task space where trajectories are guaranteed to be of bounded length We evaluate our method on two different setups with a six degree of freedom DOF UR5 as the target system First our method is validated using a seven DOF Sawyer as the demonstration system Then an extensive user study is carried out where several participants are asked to demonstrate with and without guidance a mock weld task using a hand held tool tracked by a VICON system With guidance users were able to always carry out the task successfully in comparison to only 44 of the time without guidance
dc.language	en
dc.publisher	IEEE
dc.relation	http://purl.org/au-research/grants/arc/IC200100001
dc.relation.ispartof	2023 IEEE International Conference on Robotics and Automation (ICRA)
dc.relation.ispartof	2023 IEEE International Conference on Robotics and Automation
dc.relation.isbasedon	10.1109/icra48891.2023.10160291
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	Guided Learning from Demonstration for Robust Transferability
dc.type	Conference Proceeding
utslib.citation.volume	2023-May
utslib.location.activity	London, United Kingdom
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - RI - Robotics Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2025-07-04T00:00:00+1000Z
dc.date.updated	2023-10-28T01:58:38Z
pubs.finish-date	2023-06-02
pubs.publication-status	Published
pubs.start-date	2023-05-29
pubs.volume	2023-May

Abstract:

Learning from demonstration LfD has the potential to greatly increase the applicability of robotic manipulators in modern industrial applications Recent progress in LfD methods have put more emphasis in learning robustness than in guiding the demonstration itself in order to improve robustness The latter is particularly important to consider when the target system reproducing the motion is structurally different to the demonstration system as some demonstrated motions may not be reproducible In light of this this paper introduces a new guided learning from demonstration paradigm where an interactive graphical user interface GUI guides the user during demonstration preventing them from demonstrating non reproducible motions The key aspect of our approach is determining the space of reproducible motions based on a motion planning framework which finds regions in the task space where trajectories are guaranteed to be of bounded length We evaluate our method on two different setups with a six degree of freedom DOF UR5 as the target system First our method is validated using a seven DOF Sawyer as the demonstration system Then an extensive user study is carried out where several participants are asked to demonstrate with and without guidance a mock weld task using a hand held tool tracked by a VICON system With guidance users were able to always carry out the task successfully in comparison to only 44 of the time without guidance

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/172875