Deep Samplable Observation Model for Global Localization and Kidnapping

Chen, R; Yin, H; Jiao, Y; Dissanayake, G; Wang, Y; Xiong, R

Deep Samplable Observation Model for Global Localization and Kidnapping

Chen, R Yin, H Jiao, Y Dissanayake, G

Wang, Y Xiong, R

Permalink

Publisher:: Institute of Electrical and Electronics Engineers
Publication Type:: Journal Article
Citation:: IEEE Robotics and Automation Letters, 2021, 6, (2), pp. 2296-2303
Issue Date:: 2021-02-23

Closed Access

	Filename	Description	Size
	Deep_Samplable_Observation_Model_for_Global_Localization_and_Kidnapping.pdf	Published version	2.75 MB	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	Chen, R
dc.contributor.author	Yin, H
dc.contributor.author	Jiao, Y
dc.contributor.author	Dissanayake, G https://orcid.org/0000-0002-7992-0680
dc.contributor.author	Wang, Y
dc.contributor.author	Xiong, R
dc.date.accessioned	2022-02-28T05:46:00Z
dc.date.available	2022-02-28T05:46:00Z
dc.date.issued	2021-02-23
dc.identifier.citation	IEEE Robotics and Automation Letters, 2021, 6, (2), pp. 2296-2303
dc.identifier.issn	2377-3766
dc.identifier.issn	2377-3766
dc.identifier.uri	http://hdl.handle.net/10453/154924
dc.description.abstract	Global localization and kidnapping are two challenging problems in robot localization. The popular method, Monte Carlo Localization (MCL) addresses the problem by iteratively updating a set of particles with a “sampling-weighting” loop. Sampling is decisive to the performance of MCL [1]. However, traditional MCL can only sample from a uniform distribution over the state space. Although variants of MCL propose different sampling models, they fail to provide an accurate distribution or generalize across scenes. To better deal with these problems, we present a distribution proposal model named Deep Samplable Observation Model (DSOM). DSOM takes a map and a 2D laser scan as inputs and outputs a conditional multimodal probability distribution of the pose, making the samples more focusing on the regions with higher likelihood. With such samples, the convergence is expected to be more effective and efficient. Considering that the learning-based sampling model may fail to capture the accurate pose sometimes, we furthermore propose the Adaptive Mixture MCL (AdaM MCL), which deploys a trusty mechanism to adaptively select updating mode for each particle to tolerate this situation. Equipped with DSOM, AdaM MCL can achieve more accurate estimation, faster convergence and better scalability than previous methods in both synthetic and real scenes. Even in real environments with long-term changes, AdaM MCL is able to localize the robot using DSOM trained only by simulation observations from a SLAM map or a blueprint map. Source code for this paper is available here: https://github.com/Runjian-Chen/AdaM_MCL.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers
dc.relation.ispartof	IEEE Robotics and Automation Letters
dc.relation.isbasedon	10.1109/lra.2021.3061339
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0913 Mechanical Engineering
dc.title	Deep Samplable Observation Model for Global Localization and Kidnapping
dc.type	Journal Article
utslib.citation.volume	6
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 - CAS - Centre for Autonomous Systems
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2022-02-28T05:45:58Z
pubs.issue	2
pubs.publication-status	Published
pubs.volume	6
utslib.citation.issue	2

Abstract:

Global localization and kidnapping are two challenging problems in robot localization. The popular method, Monte Carlo Localization (MCL) addresses the problem by iteratively updating a set of particles with a “sampling-weighting” loop. Sampling is decisive to the performance of MCL [1]. However, traditional MCL can only sample from a uniform distribution over the state space. Although variants of MCL propose different sampling models, they fail to provide an accurate distribution or generalize across scenes. To better deal with these problems, we present a distribution proposal model named Deep Samplable Observation Model (DSOM). DSOM takes a map and a 2D laser scan as inputs and outputs a conditional multimodal probability distribution of the pose, making the samples more focusing on the regions with higher likelihood. With such samples, the convergence is expected to be more effective and efficient. Considering that the learning-based sampling model may fail to capture the accurate pose sometimes, we furthermore propose the Adaptive Mixture MCL (AdaM MCL), which deploys a trusty mechanism to adaptively select updating mode for each particle to tolerate this situation. Equipped with DSOM, AdaM MCL can achieve more accurate estimation, faster convergence and better scalability than previous methods in both synthetic and real scenes. Even in real environments with long-term changes, AdaM MCL is able to localize the robot using DSOM trained only by simulation observations from a SLAM map or a blueprint map. Source code for this paper is available here: https://github.com/Runjian-Chen/AdaM_MCL.

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

http://hdl.handle.net/10453/154924