To Örebro University

oru.seÖrebro University Publications
Planned maintenance
A system upgrade is planned for 10/12-2024, at 12:00-13:00. During this time DiVA will be unavailable.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Online Distance Field Priors for Gaussian Process Implicit Surfaces
Örebro University, School of Science and Technology. (Autonomous Mobile Manipulation Lab, Center for Applied Autonomous Sensor Systems (AASS))ORCID iD: 0000-0002-4651-589X
Örebro University, School of Science and Technology. (Autonomous Mobile Manipulation Lab, Center for Applied Autonomous Sensor Systems (AASS))ORCID iD: 0000-0002-6013-4874
Örebro University, School of Science and Technology. (Autonomous Mobile Manipulation Lab, Center for Applied Autonomous Sensor Systems (AASS))ORCID iD: 0000-0003-3958-6179
2022 (English)In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 4, p. 8996-9003Article in journal (Refereed) Published
Abstract [en]

Gaussian process (GP) implicit surface models provide environment and object representations which elegantly address noise and uncertainty while remaining sufficiently flexible to capture complex geometry. However, GP models quickly become intractable as the size of the observation set grows-a trait which is difficult to reconcile with the rate at which modern range sensors produce data. Furthermore, naive applications of GPs to implicit surface models allocate model resources uniformly, thus using precious resources to capture simple geometry. In contrast to prior work addressing these challenges though model sparsification, spatial partitioning, or ad-hoc filtering, we propose introducing model bias online through the GP's mean function. We achieve more accurate distance fields using smaller models by creating a distance field prior from features which are easy to extract and have analytic distance fields. In particular, we demonstrate this approach using linear features. We show the proposed distance field halves model size in a 2D mapping task using data from a SICK S300 sensor. When applied to a single 3D scene from the TUM RGB-D SLAM dataset, we achieve a fivefold reduction in model size. Our proposed prior results in more accurate GP implicit surfaces, while allowing existing models to function in larger environments or with larger spatial partitions due to reduced model size.

Place, publisher, year, edition, pages
IEEE, 2022. Vol. 7, no 4, p. 8996-9003
Keywords [en]
Gaussian processes, machine learning, robot sensing systems, supervised learning
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:oru:diva-100884DOI: 10.1109/LRA.2022.3189434ISI: 000838567100055Scopus ID: 2-s2.0-85134253745OAI: oai:DiVA.org:oru-100884DiVA, id: diva2:1691786
Funder
Knut and Alice Wallenberg FoundationAvailable from: 2022-08-31 Created: 2022-08-31 Last updated: 2024-01-17Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Ivan, Jean-Paul A.Stoyanov, TodorStork, Johannes A.

Search in DiVA

By author/editor
Ivan, Jean-Paul A.Stoyanov, TodorStork, Johannes A.
By organisation
School of Science and Technology
In the same journal
IEEE Robotics and Automation Letters
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 155 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf