kth.sePublications
System disruptions
We are currently experiencing disruptions on the search portals due to high traffic. We are working to resolve the issue, you may temporarily encounter an error message.
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
Fully-Probabilistic Terrain Modelling and Localization With Stochastic Variational Gaussian Process Maps
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. (Swedish Maritime Robot Ctr SMaRC)ORCID iD: 0000-0001-8303-7826
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. (Swedish Maritime Robot Ctr SMaRC)ORCID iD: 0000-0003-4943-2501
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. (Swedish Maritime Robot Ctr SMaRC)ORCID iD: 0000-0002-7796-1438
2022 (English)In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 7, no 4, p. 8729-8736Article in journal (Refereed) Published
Abstract [en]

Gaussian processes (GPs) are becoming a standard tool to build terrain representations thanks to their capacity to model map uncertainty. This effectively yields a reliability measure of the areas of the map, which can be directly utilized by Bayes filtering algorithms in robot localization problems. A key factor is that this map uncertainty can incorporate the noise intrinsic to the terrain surveying process through the GPs ability to train on uncertain inputs (UIs). However, existing techniques to build GP maps with UIs in a tractable manner are restricted in the form and degree of the input noise. In this letter, we propose a flexible and efficient framework to build large-scale GP maps with UIs based on Stochastic Variational GPs and Monte Carlo sampling of the UIs distributions. We validate our mapping approach on a large bathymetric survey collected with an autonomous underwater vehicle (AUV) and analyze its performance against the use of deterministic inputs (DI). Finally, we show how using UI SVGP maps yields more accurate particle filter localization results than DI SVGP on a real AUV mission over an entirely predicted area.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2022. Vol. 7, no 4, p. 8729-8736
Keywords [en]
Mapping, marine robotics, localization, gaussian process
National Category
Production Engineering, Human Work Science and Ergonomics Other Environmental Engineering Environmental Management
Identifiers
URN: urn:nbn:se:kth:diva-316709DOI: 10.1109/LRA.2022.3182807ISI: 000838567100022Scopus ID: 2-s2.0-85132756292OAI: oai:DiVA.org:kth-316709DiVA, id: diva2:1691822
Note

QC 20220831

Available from: 2022-08-31 Created: 2022-08-31 Last updated: 2025-02-10Bibliographically approved
In thesis
1. Data-driven Approaches to Uncertainty Modelling for SLAM in the Open Sea
Open this publication in new window or tab >>Data-driven Approaches to Uncertainty Modelling for SLAM in the Open Sea
2022 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Autonomous underwater vehicles (AUVs) equipped with multibeam echo-sounders have become indispensable tools for bathymetric mapping due to their ability to reach seabed regions inaccessible to surface vessels. However, the closer proximity to the survey area comes at the expense of a growing error in the AUV global pose estimate due to the lack of prior maps or a geo-referencing system underwater, such as GPS. This limitation, together with the changing environment dynamics in deep sea waters and the scale of the areas to map, makes simultaneous localization and mapping (SLAM) a necessary enabler for long-range, reliable and safe AUV navigation in open sea missions.SLAM has allowed the safe deployment of self-driving cars on the streets and service robots in our homes, but remains a challenge in the deep sea domain. This is due to the constrained sensing capabilities available underwater and the scarcity of distinguishable features in the seabed. As a result of these, successful place recognition is infrequent, yielding loop closure (LC) detections more sparse and therefore more crucial. To adequately factor in each LC constraint in a SLAM back-end, their uncertainties need to be carefully parameterized to weight their influence in the final AUV trajectory estimate. Thus, this thesis is concerned with modelling these uncertainties, in particular when analytical models cannot be derived, focusing instead in data-driven methods. 

We present our contributions in three key SLAM areas targeting this problem. First, our work on inferring the uncertainties in the bathymetric submap registration process shows how deep learning techniques can be successfully applied to learning noise models directly from raw data and without ground truth position information. We further show how the predicted uncertainties improve the convergence of submap-based graph-SLAM solutions in AUV surveys.Secondly, we introduce a methodology to construct terrain representations with Stochastic Variational Gaussian processes (SVGP) propagating the AUV localization and sensors uncertainties into the final maps. The proposed approach is not limited to any GP kernel or noise model in the data and can handle datasets of millions of training points. The experiments demonstrate how the learned terrain models yield improved particle filter estimates in AUV localization problems.Finally, we adapt the previous SVGP mapping approach to online bathymetric learning and demonstrate its scalability and flexibility in a Rao-Blackwellized SLAM framework. The presented RBPF-SVGP solution is capable of maintaining up to 100 particles in parallel, each with a single SVGP map capable of regressing entire surveys. Our results show how the RBPF-SVGP can perform in real time in an embedded platform and can be executed live in an AUV.

Additionally, all the implementations proposed have been made publicly available to promote further research in underwater SLAM and the adoption of common open-source frameworks, datasets and benchmarks in the field.

Abstract [sv]

Autonoma undervattensfarkoster (AUV) utrustade med multibeam-ekolod har blivit ett oumbärligt verktyg för batymetrisk kartläggning tack vare dess förmåga att nå hahvsbottenområden som är oåtkomliga för ytfartyg.Fördelen med att kunna komma närmare till undersökningsområden kommer dock på bekostnad av ett växande fel i AUVs globala positionsuppskattning, detta på grund av bristen på tidigare kartor eller undervattens-georeferenssystem, såsom GPS.Denna begränsning, tillsammans med förändrande vattendynamik i djuphavsvatten och skalan på områden som ska kartläggas, gör att Simultaneous Localization and Mapping (SLAM) är ett måste för pålitlig och säker AUV-navigering i öppet hav för långa avstånd.

SLAM har möjliggjort säker utplacering av självkörande bilar på gator och servicerobotar i våra hem, men i djuphavsområdet är SLAM fortfarande en utmaning.Detta beror på de begränsade avkänningsmöjligheterna tillgängliga under vatten och avsaknaden på urskiljbara kännetecken i havsbotten.På grund av detta är lyckad platsigenkänning sällsynt, vilket leder till färre detektion av loop closure (LC). Varje LC blir därmed mer avgörande.För att korrekt kunna lägga in LC-begränsningar i en SLAM-backend måste deras osäkerheter noggrant parametriseras för att väga deras inflytande i den slutliga uppskattningen av AUVs kurs.Denna doktorsavhandling handlar därför om modellering av dessa osäkerheter och fokuset ligger på datadrivna metoder i tillfällen där analytiska modeller inte kan härledas.

Vi presenterar våra bidrag inom tre nyckelområden för SLAM med hänsyn till detta problem.För det första visar vårt arbete med att härleda osäkerheter i den batymetriska kartregistreringsprocessen hur djupinlärningstekniker kan tillämpas för att lära sig brusmodeller direkt från rådata och utan ground truth positionsinformation.Vidare visar vi hur de förutspådda osäkerheterna förbättrar konvergensen av submap-baserad graf-SLAM lösningar i AUV kartläggningar.För det andra introducerar vi en metodik för att konstruera terrängrepresentationer där Stochastic Variational Gaussian processes (SVGP) används för att sprida AUVs lokaliserings- och sensorosäkerheter till de slutliga batymetriska kartorna.Den föreslagna metodiken är inte begränsad till någon GP-kärna eller brusmodell i data och kan hantera dataset med miljontals träningspunkter.Experimenten visar hur de lärda terrängmodellerna förbättrar partikelfilteruppskattningar av AUV-lokalisering.Slutligen anpassar vi den tidigare nämnda SVGP-kartläggningsmetoden till online batymetriskinlärning och visar dess skalbarhet och flexibilitet i ett Rao-Blackwellized SLAM-ramverk.Den presenterade RBPF-SVGP lösningen kan köras med upp till 100 partiklar parallellt, där varje ensklid partikel har sin egen SVGP-karta över hela kartläggningsområden.Våra resultat visar hur RBPF-SVGP kan tillämpas i realtid i en inbyggd plattform och kan utföras live i en AUV.

Vidare har alla föreslagna implementeringar gjorts allmänt tillgängliga för att främja vidare forskning inom undervattens-SLAM och antagande av gemensamma ramverk med öppen källkod, dataset och benchmark inom forskningsområdet.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2022. p. 44
Series
TRITA-EECS-AVL ; 2022:70
National Category
Robotics and automation
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-321605 (URN)978-91-8040-402-0 (ISBN)
Public defence
2022-12-15, https://kth-se.zoom.us/j/69562986585, Kollegiesalen, Brinellvägen 6, Stockholm, Stockholm, 14:00 (English)
Opponent
Supervisors
Note

QC 20221128

Available from: 2022-11-28 Created: 2022-11-25 Last updated: 2025-02-09Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Torroba, IgnacioSprague, ChristopherFolkesson, John

Search in DiVA

By author/editor
Torroba, IgnacioSprague, ChristopherFolkesson, John
By organisation
Robotics, Perception and Learning, RPL
In the same journal
IEEE Robotics and Automation Letters
Production Engineering, Human Work Science and ErgonomicsOther Environmental EngineeringEnvironmental Management

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 244 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