Log-GPIS-MOP: A Unified Representation for Mapping, Odometry, and Planning

Wu, L; Lee, KMB; Le Gentil, C; Vidal-Calleja, T

Log-GPIS-MOP: A Unified Representation for Mapping, Odometry, and Planning

Wu, L

Lee, KMB Le Gentil, C

Vidal-Calleja, T

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Robotics, 2023, 39, (5), pp. 4078-4094
Issue Date:: 2023-10-01

Closed Access

	Filename	Description	Size
	Log-GPIS-MOP_A_Unified_Representation_for_Mapping_Odometry_and_Planning.pdf	Published version	3.37 MB		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	Wu, L https://orcid.org/0000-0002-6295-5529
dc.contributor.author	Lee, KMB
dc.contributor.author	Le Gentil, C https://orcid.org/0000-0002-9790-5935
dc.contributor.author	Vidal-Calleja, T
dc.date.accessioned	2023-11-06T05:14:15Z
dc.date.available	2023-11-06T05:14:15Z
dc.date.issued	2023-10-01
dc.identifier.citation	IEEE Transactions on Robotics, 2023, 39, (5), pp. 4078-4094
dc.identifier.issn	1552-3098
dc.identifier.issn	1941-0468
dc.identifier.uri	http://hdl.handle.net/10453/173050
dc.description.abstract	Whereas dedicated scene representations are required for each different task in conventional robotic systems, this article demonstrates that a unified representation can be used directly for multiple key tasks. We propose the log-Gaussian process implicit surface for mapping, odometry, and planning (Log-GPIS-MOP): a probabilistic framework for surface reconstruction, localization, and navigation based on a unified representation. Our framework applies a logarithmic transformation to a Gaussian process implicit surface (GPIS) formulation to recover a global representation that accurately captures the Euclidean distance field with gradients and, at the same time, the implicit surface. By directly estimating the distance field and its gradient through Log-GPIS inference, the proposed incremental odometry technique computes the optimal alignment of an incoming frame and fuses it globally to produce a map. Concurrently, an optimization-based planner computes a safe collision-free path using the same Log-GPIS surface representation. We validate the proposed framework on simulated and real datasets in 2-D and 3-D, and benchmark against the state-of-the-art approaches. Our experiments show that Log-GPIS-MOP produces competitive results in sequential odometry, surface mapping, and obstacle avoidance.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation	http://purl.org/au-research/grants/arc/DP210101336
dc.relation.ispartof	IEEE Transactions on Robotics
dc.relation.isbasedon	10.1109/TRO.2023.3296982
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering, 0913 Mechanical Engineering
dc.subject.classification	Industrial Engineering & Automation
dc.subject.classification	4007 Control engineering, mechatronics and robotics
dc.title	Log-GPIS-MOP: A Unified Representation for Mapping, Odometry, and Planning
dc.type	Journal Article
utslib.citation.volume	39
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	0913 Mechanical Engineering
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	closed_access	*
dc.date.updated	2023-11-06T05:14:13Z
pubs.issue	5
pubs.publication-status	Published
pubs.volume	39
utslib.citation.issue	5

Abstract:

Whereas dedicated scene representations are required for each different task in conventional robotic systems, this article demonstrates that a unified representation can be used directly for multiple key tasks. We propose the log-Gaussian process implicit surface for mapping, odometry, and planning (Log-GPIS-MOP): a probabilistic framework for surface reconstruction, localization, and navigation based on a unified representation. Our framework applies a logarithmic transformation to a Gaussian process implicit surface (GPIS) formulation to recover a global representation that accurately captures the Euclidean distance field with gradients and, at the same time, the implicit surface. By directly estimating the distance field and its gradient through Log-GPIS inference, the proposed incremental odometry technique computes the optimal alignment of an incoming frame and fuses it globally to produce a map. Concurrently, an optimization-based planner computes a safe collision-free path using the same Log-GPIS surface representation. We validate the proposed framework on simulated and real datasets in 2-D and 3-D, and benchmark against the state-of-the-art approaches. Our experiments show that Log-GPIS-MOP produces competitive results in sequential odometry, surface mapping, and obstacle avoidance.

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

http://hdl.handle.net/10453/173050