Context-aware 3D object anchoring for mobile robots

DC FieldValueLanguage
dc.contributor.authorGuenther, Martin
dc.contributor.authorRuiz-Sarmiento, J. R.
dc.contributor.authorGalindo, Cipriano
dc.contributor.authorGonzalez-Jimenez, Javier
dc.contributor.authorHertzberg, Joachim
dc.date.accessioned2021-12-23T16:16:09Z-
dc.date.available2021-12-23T16:16:09Z-
dc.date.issued2018
dc.identifier.issn09218890
dc.identifier.urihttps://osnascholar.ub.uni-osnabrueck.de/handle/unios/11749-
dc.description.abstractA world model representing the elements in a robot's environment needs to maintain a correspondence between the objects being observed and their internal representations, which is known as the anchoring problem. Anchoring is a key aspect for an intelligent robot operation, since it enables high-level functions such as task planning and execution. This work presents an anchoring system that continually integrates new observations from a 3D object recognition algorithm into a probabilistic world model. Our system takes advantage of the contextual relations inherent to human-made spaces in order to improve the classification results of the baseline object recognition system. To achieve that, the system builds a graph based world model containing the objects in the scene (both in the current and previously perceived observations), which is exploited by a Probabilistic Graphical Model (PGM) in order to leverage contextual information during recognition. The world model also enables the system to exploit information about objects beyond the current field of view of the robot sensors. Most importantly, this is done in an online fashion, overcoming both the disadvantages of single-shot recognition systems (e.g., limited sensor aperture) and offline recognition systems that require prior registration of all frames of a scene (e.g., dynamic scenes, unsuitability for plan-based robot control). We also propose a novel way to include the outcome of local object recognition methods in the PGM, which results in a decrease in the usually high model learning complexity and an increase in the system performance. The system performance has been assessed with a dataset collected by a mobile robot from restaurant-like settings, obtaining positive results for both its data association and object recognition capabilities. The system has been successfully used in the RACE robotic architecture. (C) 2018 Elsevier B.V. All rights reserved.
dc.description.sponsorshipEuropean project RACE, Germany [FP7-ICT-2011-7, 287752]; European project MoveCare, Italy [H2020-ICT-2016-1, 732158]; WISER project - Spanish Government, Spain [DPI2017-84827-R]; European Regional Development's funds (FEDER), Spain; I-PPIT-UMA program - University of Malaga, Spain; This work is supported by the European projects RACE, Germany (FP7-ICT-2011-7, grant agreement number 287752) and MoveCare, Italy (H2020-ICT-2016-1, grant agreement number 732158), by the WISER project (reference DPI2017-84827-R) funded by the Spanish Government, Spain and financed by European Regional Development's funds (FEDER), Spain, and by a postdoc contract from the I-PPIT-UMA program financed by the University of Malaga, Spain.
dc.language.isoen
dc.publisherELSEVIER SCIENCE BV
dc.relation.ispartofROBOTICS AND AUTONOMOUS SYSTEMS
dc.subjectAnchoring
dc.subjectAutomation & Control Systems
dc.subjectComputer Science
dc.subjectComputer Science, Artificial Intelligence
dc.subjectConditional random fields
dc.subjectContext-aware anchoring
dc.subjectData association
dc.subjectFEATURES
dc.subjectMAPS
dc.subjectMobile robotics
dc.subjectRECOGNITION
dc.subjectRobotics
dc.subjectTEXTURE
dc.subjectWorld modeling
dc.titleContext-aware 3D object anchoring for mobile robots
dc.typejournal article
dc.identifier.doi10.1016/j.robot.2018.08.016
dc.identifier.isiISI:000451791600002
dc.description.volume110
dc.description.startpage12
dc.description.endpage32
dc.contributor.orcid0000-0003-2922-1969
dc.contributor.orcid0000-0003-3845-3497
dc.contributor.orcid0000-0003-2922-1969
dc.contributor.orcid0000-0002-9929-5309
dc.contributor.orcid0000-0003-2276-3140
dc.contributor.researcheridAAD-9158-2020
dc.contributor.researcheridD-5774-2011
dc.contributor.researcheridD-5861-2011
dc.contributor.researcheridH-6180-2019
dc.identifier.eissn1872793X
dc.publisher.placePO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS
dcterms.isPartOf.abbreviationRobot. Auton. Syst.
crisitem.author.netidHeJo177-
Show simple item record

Page view(s)

2
Last Week
0
Last month
0
checked on Apr 23, 2024

Google ScholarTM

Check

Altmetric