Show simple item record

dc.contributor.authorGao, Cen
dc.contributor.authorHarle, Roberten
dc.date.accessioned2017-03-30T12:15:37Z
dc.date.available2017-03-30T12:15:37Z
dc.date.issued2017-07-24en
dc.identifier.issn1050-4729
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/263350
dc.description.abstractSimultaneous Localisation and Mapping (SLAM) systems that recover the trajectory of a robot or mobile device are characterised by a front-end and back-end. The front-end uses sensor observations to identify loop closures; the back-end optimises the estimated trajectory to be consistent with these closures. The GraphSLAM framework formulates the back-end problem as a graph-based optimisation on a pose graph. This paper describes a back-end system optimised for very dense sequence-based loop closures. This arises when the front-end generates magnetic loop closures, among other things. Magnetic measurements are fast varying, which is good for localisation, but the requirement for high sampling rates (50 Hz+) produces many more loop closures than conventional systems. To date, however, there is no study optimising GraphSLAM back-end for sequence-based magnetic loop closures. Hence we introduce a novel variant of the Stochastic Gradient Descent-based SLAM algorithm called MSGD (Magnetic-SGD). We use high-accuracy groundtruth system and extensive real datasets to evaluate MSGD against state-of-the-art back-end algorithms. We demonstrate MSGD is at least as good as the best competitor algorithm in terms of quality, while being faster and more scalable.
dc.languageEnglishen
dc.language.isoenen
dc.publisherIEEE
dc.subjectsimultaneous localization and mappingen
dc.subjecttrajectoryen
dc.subjectalgorithm design and analysisen
dc.subjectestimationen
dc.subjectoptimizationen
dc.titleMSGD: Scalable Back-end for Indoor Magnetic Field-based GraphSLAMen
dc.typeConference Object
prism.publicationDate2017en
prism.publicationName2017 IEEE International Conference on Robotics and Automation (ICRA)en
dc.identifier.doi10.17863/CAM.8686
dcterms.dateAccepted2017-01-15en
rioxxterms.versionofrecord10.1109/ICRA.2017.7989444en
rioxxterms.versionAMen
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2017-07-24en
dc.contributor.orcidHarle, Robert [0000-0001-7201-9075]
rioxxterms.typeConference Paper/Proceeding/Abstracten
cam.issuedOnline2017-07-24en
pubs.conference-nameICRA 2017en
pubs.conference-start-date2017-05-29en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record