Probabilistic active filtering for object search in clutter

Poon, J; Cui, Y; Ooga, J; Ogawa, A; Matsubara, T

Probabilistic active filtering for object search in clutter

Poon, J Cui, Y Ooga, J Ogawa, A Matsubara, T

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: Proceedings - IEEE International Conference on Robotics and Automation, 2019, 2019-May, pp. 7256-7261
Issue Date:: 2019-05-01

Closed Access

	Filename	Description	Size
	08794418.pdf	Published version	380.8 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Poon, J
dc.contributor.author	Cui, Y
dc.contributor.author	Ooga, J
dc.contributor.author	Ogawa, A
dc.contributor.author	Matsubara, T
dc.date	2019-05-20
dc.date.accessioned	2020-06-12T20:51:19Z
dc.date.available	2020-06-12T20:51:19Z
dc.date.issued	2019-05-01
dc.identifier.citation	Proceedings - IEEE International Conference on Robotics and Automation, 2019, 2019-May, pp. 7256-7261
dc.identifier.isbn	9781538660263
dc.identifier.issn	1050-4729
dc.identifier.uri	http://hdl.handle.net/10453/141393
dc.description.abstract	© 2019 IEEE. This paper proposes a probabilistic approach for object search in clutter. Due to heavy occlusions, it is vital for an agent to be able to gradually reduce uncertainty in observations of the objects in its workspace by systematically rearranging them. Probabilistic methodologies present a promising sample-efficient alternative to handle the massively complex state-action space that inherently comes with this problem, avoiding the need for both exhaustive training samples and the accompanying heuristics for traversing a large-scale model during runtime. We approach the object search problem by extending a Gaussian Process active filtering strategy with an additional model for capturing state dynamics as the objects are moved over the course of the activity. This allows viable models to be built upon relatively scarce training data, while the complexity of the action space is also reduced by shifting objects over relatively short distances. Validation in both simulation and with a real Baxter robot with a limited number of training samples demonstrates the efficacy of the proposed approach.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	Proceedings - IEEE International Conference on Robotics and Automation
dc.relation.ispartof	International Conference on Robotics and Automation
dc.relation.isbasedon	10.1109/ICRA.2019.8794418
dc.rights	© 2019 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.	en_US
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.title	Probabilistic active filtering for object search in clutter
dc.type	Conference Proceeding
utslib.citation.volume	2019-May
utslib.location.activity	Montreal, QC, Canada
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Students
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2020-06-12T20:51:15Z
pubs.finish-date	2019-05-24
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2019-05-20
pubs.volume	2019-May
dc.location	Piscataway, USA

Abstract:

© 2019 IEEE. This paper proposes a probabilistic approach for object search in clutter. Due to heavy occlusions, it is vital for an agent to be able to gradually reduce uncertainty in observations of the objects in its workspace by systematically rearranging them. Probabilistic methodologies present a promising sample-efficient alternative to handle the massively complex state-action space that inherently comes with this problem, avoiding the need for both exhaustive training samples and the accompanying heuristics for traversing a large-scale model during runtime. We approach the object search problem by extending a Gaussian Process active filtering strategy with an additional model for capturing state dynamics as the objects are moved over the course of the activity. This allows viable models to be built upon relatively scarce training data, while the complexity of the action space is also reduced by shifting objects over relatively short distances. Validation in both simulation and with a real Baxter robot with a limited number of training samples demonstrates the efficacy of the proposed approach.

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

http://hdl.handle.net/10453/141393