CARE: Confidence-Rich Autonomous Robot Exploration Using Bayesian Kernel Inference and Optimization

Xu, Y; Zheng, R; Zhang, S; Liu, M; Huang, S

CARE: Confidence-Rich Autonomous Robot Exploration Using Bayesian Kernel Inference and Optimization

Xu, Y Zheng, R Zhang, S Liu, M Huang, S

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Robotics and Automation Letters, 2023, 8, (10), pp. 6755-6762
Issue Date:: 2023-10-01

Embargoed

	Filename	Description	Size
	CARE Confidence-Rich Autonomous Robot Exploration Using Bayesian Kernel Inference and Optimization.pdf	Accepted version	1.71 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 7 Sep 2025

Full metadata record

Field	Value	Language
dc.contributor.author	Xu, Y
dc.contributor.author	Zheng, R
dc.contributor.author	Zhang, S
dc.contributor.author	Liu, M
dc.contributor.author	Huang, S https://orcid.org/0000-0002-6124-4178
dc.date.accessioned	2023-11-06T05:25:28Z
dc.date.available	2023-11-06T05:25:28Z
dc.date.issued	2023-10-01
dc.identifier.citation	IEEE Robotics and Automation Letters, 2023, 8, (10), pp. 6755-6762
dc.identifier.issn	2377-3766
dc.identifier.issn	2377-3766
dc.identifier.uri	http://hdl.handle.net/10453/173054
dc.description.abstract	In this letter, we consider improving the efficiency of information-based autonomous robot exploration in unknown and complex environments. We first utilize Gaussian process (GP) regression to learn a surrogate model to infer the confidence-rich mutual information (CRMI) of querying control actions, then adopt an objective function consisting of predicted CRMI values and prediction uncertainties to conduct Bayesian optimization (BO), i.e., GP-based BO (GPBO). The trade-off between the best action with the highest CRMI value (exploitation) and the action with high prediction variance (exploration) can be realized. To further improve the efficiency of GPBO, we propose a novel lightweight information gain inference method based on Bayesian kernel inference and optimization (BKIO), achieving an approximate logarithmic complexity without the need for training. BKIO can also infer the CRMI and generate the best action using BO with bounded cumulative regret, which ensures its comparable accuracy to GPBO with much higher efficiency. Extensive numerical and real-world experiments show the desired efficiency of our proposed methods without losing exploration performance in different unstructured, cluttered environments.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Robotics and Automation Letters
dc.relation.isbasedon	10.1109/LRA.2023.3313054
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.rights	©2023 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.
dc.subject	0913 Mechanical Engineering
dc.subject.classification	4007 Control engineering, mechatronics and robotics
dc.subject.classification	4602 Artificial intelligence
dc.title	CARE: Confidence-Rich Autonomous Robot Exploration Using Bayesian Kernel Inference and Optimization
dc.type	Journal Article
utslib.citation.volume	8
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	embargoed	*
utslib.copyright.embargo	2025-09-07T00:00:00+1000Z
dc.date.updated	2023-11-06T05:25:27Z
pubs.issue	10
pubs.publication-status	Published
pubs.volume	8
utslib.citation.issue	10

Abstract:

In this letter, we consider improving the efficiency of information-based autonomous robot exploration in unknown and complex environments. We first utilize Gaussian process (GP) regression to learn a surrogate model to infer the confidence-rich mutual information (CRMI) of querying control actions, then adopt an objective function consisting of predicted CRMI values and prediction uncertainties to conduct Bayesian optimization (BO), i.e., GP-based BO (GPBO). The trade-off between the best action with the highest CRMI value (exploitation) and the action with high prediction variance (exploration) can be realized. To further improve the efficiency of GPBO, we propose a novel lightweight information gain inference method based on Bayesian kernel inference and optimization (BKIO), achieving an approximate logarithmic complexity without the need for training. BKIO can also infer the CRMI and generate the best action using BO with bounded cumulative regret, which ensures its comparable accuracy to GPBO with much higher efficiency. Extensive numerical and real-world experiments show the desired efficiency of our proposed methods without losing exploration performance in different unstructured, cluttered environments.

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

http://hdl.handle.net/10453/173054