kth.sePublications
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
Data-driven Approaches to Uncertainty Modelling for SLAM in the Open Sea
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0001-8303-7826
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: urn:nbn:se:kth:diva-321605ISBN: 978-91-8040-402-0 (print)OAI: oai:DiVA.org:kth-321605DiVA, id: diva2:1713621
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
List of papers
1. A Comparison of Submap Registration Methods for Multibeam Bathymetric Mapping
Open this publication in new window or tab >>A Comparison of Submap Registration Methods for Multibeam Bathymetric Mapping
2018 (English)In: AUV 2018 - 2018 IEEE/OES Autonomous Underwater Vehicle Workshop, Proceedings, Institute of Electrical and Electronics Engineers Inc. , 2018Conference paper, Published paper (Refereed)
Abstract [en]

On-the-fly registration of overlapping multibeam images is important for path planning by AUVs performing underwater surveys. In order to meet specification on such things as survey accuracy, coverage and density, precise corrections to the AUV trajectory while underway are required. There are fast methods for aligning point clouds that have been developed for robots. We compare several state of the art methods to align point clouds of large, unstructured, sub-aquatic areas to build a global map. We first collect the multibeam point clouds into smaller submaps that are then aligned using variations of the ICP algorithm. This alignment step can be applied if the error in AUV pose is small. It would be the final step in correcting a larger error on loop closing where a place recognition and a rough alignment would precede it. In the case of a lawn mower pattern survey it would be making more continuous corrections to small errors in the overlap between parallel lines. In this work we compare different methods for registration in order to determine the most suitable one for underwater terrain mapping. To do so, we benchmark the current state of the art solutions according to an error metrics and show the results.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2018
Keywords
Autonomous vehicles, Errors, Lawn mowers, Mapping, Motion planning, Surveys, ICP algorithms, Place recognition, Registration methods, State of the art, State-of-the-art methods, Survey accuracy, Terrain mapping, Underwater surveys, Autonomous underwater vehicles
National Category
Robotics and automation
Identifiers
urn:nbn:se:kth:diva-262474 (URN)10.1109/AUV.2018.8729731 (DOI)000492901600029 ()2-s2.0-85068333120 (Scopus ID)9781728102535 (ISBN)
Conference
2018 IEEE/OES Autonomous Underwater Vehicle Workshop, AUV 2018, 6 November 2018 through 9 November 2018, Porto, Portugal
Note

QC 20191017

Available from: 2019-10-17 Created: 2019-10-17 Last updated: 2025-02-09Bibliographically approved
2. Towards Autonomous Industrial-Scale Bathymetric Surveying
Open this publication in new window or tab >>Towards Autonomous Industrial-Scale Bathymetric Surveying
2019 (English)In: IEEE International Conference on Intelligent Robots and Systems, Institute of Electrical and Electronics Engineers (IEEE) , 2019, p. 6377-6382Conference paper, Published paper (Refereed)
Abstract [en]

Both higher efficiency and cost reduction can be gained from automating bathymetric surveying for offshore applications such as pipeline, telecommunication or power cables installation and inspection on the seabed. We present a SLAM system that optimizes the geo-referencing of bathymetry surveys by fusing the dead-reckoning sensor data from the surveying vehicle with constraints from the maximization of the geometric consistency of overlapping regions of the survey. The framework has been extensively tested on bathymetric maps from both simulation and several actual industrial surveys and has proved robustness over different types of terrain. We demonstrate that our system is able to maximize the consistency of the final map even when there are large sections of the survey with reduced topographic variation. The framework has been made publicly available together with the simulation environment used to test it and some of the datasets. 

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2019
Keywords
Bathymetry, Cost reduction, Intelligent robots, Maps, Offshore oil well production, Offshore pipelines, Dead reckoning sensors, Georeferencing, Higher efficiency, Industrial scale, Industrial surveys, Offshore applications, Overlapping regions, Simulation environment, Hydrographic surveys
National Category
Robotics and automation
Identifiers
urn:nbn:se:kth:diva-274145 (URN)10.1109/IROS40897.2019.8968241 (DOI)000544658405006 ()2-s2.0-85081156581 (Scopus ID)
Conference
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019, Macau, SAR, China, November 3-8, 2019
Note

QC 20200623

Available from: 2020-06-23 Created: 2020-06-23 Last updated: 2025-02-09Bibliographically approved
3. PointNetKL: Deep Inference for GICP Covariance Estimation in Bathymetric SLAM
Open this publication in new window or tab >>PointNetKL: Deep Inference for GICP Covariance Estimation in Bathymetric SLAM
2020 (English)In: IEEE Robotics and Automation Letters, E-ISSN 2377-3766, Vol. 5, no 3, p. 4078-4085Article in journal (Refereed) Published
Abstract [en]

Registration methods for point clouds have become a key component of many SLAM systems on autonomous vehicles. However, an accurate estimate of the uncertainty of such registration is a key requirement to a consistent fusion of this kind of measurements in a SLAM filter. This estimate, which is normally given as a covariance in the transformation computed between point cloud reference frames, has been modelled following different approaches, among which the most accurate is considered to be the Monte Carlo method. However, a Monte Carlo approximation is cumbersome to use inside a time-critical application such as online SLAM. Efforts have been made to estimate this covariance via machine learning using carefully designed features to abstract the raw point clouds. However, the performance of this approach is sensitive to the features chosen. We argue that it is possible to learn the features along with the covariance by working with the raw data and thus we propose a new approach based on PointNet. In this work, we train this network using the KL divergence between the learned uncertainty distribution and one computed by the Monte Carlo method as the loss. We test the performance of the general model presented applying it to our target use-case of SLAM with an autonomous underwater vehicle (AUV) restricted to the 2-dimensional registration of 3D bathymetric point clouds.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2020
Keywords
SLAM, novel deep learning methods, marine robotics, simultaneous localization and mapping, robot learning, unmanned underwater vehicles
National Category
Computer graphics and computer vision
Identifiers
urn:nbn:se:kth:diva-276602 (URN)10.1109/LRA.2020.2988180 (DOI)000536185200002 ()2-s2.0-85084935128 (Scopus ID)
Note

QC 20200623

Available from: 2020-06-23 Created: 2020-06-23 Last updated: 2025-02-07Bibliographically approved
4. Fully-Probabilistic Terrain Modelling and Localization With Stochastic Variational Gaussian Process Maps
Open this publication in new window or tab >>Fully-Probabilistic Terrain Modelling and Localization With Stochastic Variational Gaussian Process Maps
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
Keywords
Mapping, marine robotics, localization, gaussian process
National Category
Production Engineering, Human Work Science and Ergonomics Other Environmental Engineering Environmental Management
Identifiers
urn:nbn:se:kth:diva-316709 (URN)10.1109/LRA.2022.3182807 (DOI)000838567100022 ()2-s2.0-85132756292 (Scopus ID)
Note

QC 20220831

Available from: 2022-08-31 Created: 2022-08-31 Last updated: 2025-02-10Bibliographically approved
5. Online Stochastic Variational Gaussian Process Mapping for Large-Scale SLAM in Real Time
Open this publication in new window or tab >>Online Stochastic Variational Gaussian Process Mapping for Large-Scale SLAM in Real Time
Show others...
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Rao-Blackwellized particle filter (RBPF) SLAM solutions with Gaussian Process (GP) maps can both maintain multiple hypotheses of a vehicle pose estimate and perform implicit data association for loop closure detection in continuous terrain representations. Both qualities are of particular interest for SLAM with autonomous underwater vehicles (AUVs) in the open sea, where distinguishable features are scarce. However, the applicability of GP regression to parallel, real-time mapping in an RBPF framework remains limited by the size of the survey and the computational cost of the GP training. To overcome these constraints, in this letter we propose the adaption of Stochastic Variational GP (SVGP) regression to online mapping in combination with a novel, efficient particle trajectory storing in the RBPF. We show how the resulting RBPF-SVGP framework can achieve real-time performance in an embedded platform on two AUV surveys containing millions of points. We further test the framework on a live mission on an AUV and we make the implementation publicly available.

Keywords
Maritime Robotics, SLAM, Gaussian Process
National Category
Computer graphics and computer vision
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-321603 (URN)
Projects
SMaRC
Note

QC 20221206

Available from: 2022-11-18 Created: 2022-11-18 Last updated: 2025-02-07Bibliographically approved

Open Access in DiVA

fulltext(16023 kB)952 downloads
File information
File name FULLTEXT01.pdfFile size 16023 kBChecksum SHA-512
c8851fe705cb7819cadee371f1160b5fed8b03c52327f5b6da61065560db126529a759ecfeedfcbd2144476ba9c31f341ffdf1a9a6520daa4da8d22b64420dec
Type fulltextMimetype application/pdf

Authority records

Torroba, Ignacio

Search in DiVA

By author/editor
Torroba, Ignacio
By organisation
Robotics, Perception and Learning, RPL
Robotics and automation

Search outside of DiVA

GoogleGoogle Scholar
Total: 956 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1790 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