Intelligent low-cost solutions for underwater intervention using computer vision and machine learning
This thesis considers intelligent solutions that facilitates for autonomous technology in underwater intervention and navigation. A special focus have been on implementing methods and solutions in inspection, maintenance, and repair (IMR) operations using low cost equipment. The presented work invol...
Published in: | OCEANS 2019 - Marseille |
---|---|
Main Author: | |
Other Authors: | , , |
Format: | Doctoral or Postdoctoral Thesis |
Language: | English |
Published: |
NTNU
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/11250/3047839 |
id |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/3047839 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
NTNU Open Archive (Norwegian University of Science and Technology) |
op_collection_id |
ftntnutrondheimi |
language |
English |
topic |
VDP::Technology: 500::Marine technology: 580 |
spellingShingle |
VDP::Technology: 500::Marine technology: 580 Skaldebø, Martin Breivik Intelligent low-cost solutions for underwater intervention using computer vision and machine learning |
topic_facet |
VDP::Technology: 500::Marine technology: 580 |
description |
This thesis considers intelligent solutions that facilitates for autonomous technology in underwater intervention and navigation. A special focus have been on implementing methods and solutions in inspection, maintenance, and repair (IMR) operations using low cost equipment. The presented work involves development and implementation of solutions to increase the efficiency and safety of operations, and includes both theoretical contributions and experimental testing. The work includes learning algorithms to improve visual authenticity of simulators and digital twin scenarios, computer vision in guidance and navigation of underwater vehicles and intervention systems, development and testing of novel equipment, and experimental verification of presented methods and equipment. The introduction of advanced learning algorithms enables systems to perform tasks that was previous too complex and complicated for any modelled solutions. This thesis explores the use of generative adversarial networks to improve the realism of simulated environments, which again will improve the transferred learning between simulated environments and real world operations. Such a mapping between domains is complex to model, especially in the underwater scene given the intricate scenery with scattering of light and marine particles. Machine learning algorithms provides new solutions for this mapping, and can aid in improving result from simulation tools to have greater impact on real world operations. In the same way humans uses their senses to experience life, autonomous systems requires sensory feedback to act and react upon. A sensor is only as effective as the information that can be extracted from the sensory output, and increasing and strengthening this information will improve the support from the sensor. Camera footage contain information with higher spatial and temporal resolution than acoustic information, and utilizing this information to its full will improve today's sensory systems. This thesis explores the use of visual aid and ... |
author2 |
Schjølberg, Ingrid Utne, Ingrid Bouwer Haugaløkken, Bent. O. A. |
format |
Doctoral or Postdoctoral Thesis |
author |
Skaldebø, Martin Breivik |
author_facet |
Skaldebø, Martin Breivik |
author_sort |
Skaldebø, Martin Breivik |
title |
Intelligent low-cost solutions for underwater intervention using computer vision and machine learning |
title_short |
Intelligent low-cost solutions for underwater intervention using computer vision and machine learning |
title_full |
Intelligent low-cost solutions for underwater intervention using computer vision and machine learning |
title_fullStr |
Intelligent low-cost solutions for underwater intervention using computer vision and machine learning |
title_full_unstemmed |
Intelligent low-cost solutions for underwater intervention using computer vision and machine learning |
title_sort |
intelligent low-cost solutions for underwater intervention using computer vision and machine learning |
publisher |
NTNU |
publishDate |
2023 |
url |
https://hdl.handle.net/11250/3047839 |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
Doctoral theses at NTNU;2023:27 Paper 1: Skaldebø, Martin Breivik; Sans-Muntadas, Albert; Schjølberg, Ingrid. Transfer Learning in Underwater Operations. I: Proceedings of OCEANS 2019 - Marseille. IEEE 2019 https://doi.org/10.1109/OCEANSE.2019.8867288 Paper 2: Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Schjølberg, Ingrid. Dynamic Positioning of an Underwater Vehicle using Monocular Vision-Based Object Detection with Machine Learning. I: Proceedings of OCEANS 2019 MTS/IEEE SEATTLE. IEEE 2019 https://doi.org/10.23919/OCEANS40490.2019.8962583 Paper 3: Haugaløkken, Bent Oddvar Arnesen; Skaldebø, Martin Breivik; Schjølberg, Ingrid. Monocular vision-based gripping of objects. Robotics and Autonomous Systems 2020 ;Volum 131. https://doi.org/10.1016/j.robot.2020.103589 This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). Paper 4: Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Schjølberg, Ingrid. SeaArm-2 - Fully electric underwater manipulator with integrated end-effector camera. I: 2021 European Control Conference, ECC 2021. IEEE conference proceedings 2021 s. 236-242 https://doi.org/10.23919/ECC54610.2021.9655121 Paper 5: Sans-Muntadas, Albert; Skaldebø, Martin Breivik; Nielsen, Mikkel Cornelius; Schjølberg, Ingrid. Unsupervised Domain Transfer for Task Automation in Unmanned Underwater Vehicle Intervention Operations. IEEE Journal of Oceanic Engineering 2022 ;Volum 47.(2) s. 312-321 https://doi.org/10.1109/JOE.2021.3126016 Paper 6: Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Schjølberg, Ingrid. Autonomous underwater grasping using a novel vision-based distance estimator Paper 7: Skaldebø, Martin Breivik; Schjølberg, Ingrid; Haugaløkken, Bent Oddvar Arnesen. Underwater Vehicle Manipulator System (UVMS) With BlueROV2 and SeaArm-2 Manipulator. I: ASME 2022 41st International Conference on Ocean, Offshore and Arctic Engineering Volume 5B: Ocean Engineering; Honoring Symposium for Professor Günther F. Clauss on Hydrodynamics and Ocean Engineering. Paper No: OMAE2022-79913, V05BT06A022; s. 1-8 https://doi.org/10.1115/OMAE2022-79913 Paper 8: Skaldebø, Martin Breivik; Schjølberg, Ingrid. Dynamic Bayesian Networks for Reduced Uncertainty in Underwater Operations. IFAC-PapersOnLine 2022 ;Volum 55. s. 409-414 https://doi.org/10.1016/j.ifacol.2022.10.462 This is an open access article under the CC BY-NC-ND license. Paper 9: Transeth, Aksel Andreas; Schjølberg, Ingrid; Lekkas, Anastasios M.; Risholm, Petter; Mohammed, Ahmed Kedir; Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Bjerkeng, Magnus Christian; Tsiourva, Maria Efstathia; Py, Frédéric. Autonomous subsea intervention (SEAVENTION). 14th IFAC Conference on Control Applications in Marine Systems, Robotics and Vehicles (CAMS 2022) https://doi.org/10.1016/j.ifacol.2022.10.459 This is an open access article under the CC BY-NC-ND license Paper 10: Skaldebø, Martin Breivik; Schjølberg,Ingrid; Haugaløkken, Bent Oddvar Arnesen System integration of underwater vehicle manipulator system (UVMS) for autonomous grasping urn:isbn:978-82-326-5480-2 urn:issn:2703-8084 https://hdl.handle.net/11250/3047839 |
op_doi |
https://doi.org/10.1109/OCEANSE.2019.8867288 https://doi.org/10.23919/OCEANS40490.2019.8962583 https://doi.org/10.1016/j.robot.2020.103589 https://doi.org/10.23919/ECC54610.2021.9655121 https://doi.org/10.1109/JOE.2021.3126016 https://doi.org/10 |
container_title |
OCEANS 2019 - Marseille |
container_start_page |
1 |
op_container_end_page |
8 |
_version_ |
1766302493567877120 |
spelling |
ftntnutrondheimi:oai:ntnuopen.ntnu.no:11250/3047839 2023-05-15T14:28:19+02:00 Intelligent low-cost solutions for underwater intervention using computer vision and machine learning Skaldebø, Martin Breivik Schjølberg, Ingrid Utne, Ingrid Bouwer Haugaløkken, Bent. O. A. 2023 application/pdf https://hdl.handle.net/11250/3047839 eng eng NTNU Doctoral theses at NTNU;2023:27 Paper 1: Skaldebø, Martin Breivik; Sans-Muntadas, Albert; Schjølberg, Ingrid. Transfer Learning in Underwater Operations. I: Proceedings of OCEANS 2019 - Marseille. IEEE 2019 https://doi.org/10.1109/OCEANSE.2019.8867288 Paper 2: Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Schjølberg, Ingrid. Dynamic Positioning of an Underwater Vehicle using Monocular Vision-Based Object Detection with Machine Learning. I: Proceedings of OCEANS 2019 MTS/IEEE SEATTLE. IEEE 2019 https://doi.org/10.23919/OCEANS40490.2019.8962583 Paper 3: Haugaløkken, Bent Oddvar Arnesen; Skaldebø, Martin Breivik; Schjølberg, Ingrid. Monocular vision-based gripping of objects. Robotics and Autonomous Systems 2020 ;Volum 131. https://doi.org/10.1016/j.robot.2020.103589 This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). Paper 4: Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Schjølberg, Ingrid. SeaArm-2 - Fully electric underwater manipulator with integrated end-effector camera. I: 2021 European Control Conference, ECC 2021. IEEE conference proceedings 2021 s. 236-242 https://doi.org/10.23919/ECC54610.2021.9655121 Paper 5: Sans-Muntadas, Albert; Skaldebø, Martin Breivik; Nielsen, Mikkel Cornelius; Schjølberg, Ingrid. Unsupervised Domain Transfer for Task Automation in Unmanned Underwater Vehicle Intervention Operations. IEEE Journal of Oceanic Engineering 2022 ;Volum 47.(2) s. 312-321 https://doi.org/10.1109/JOE.2021.3126016 Paper 6: Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Schjølberg, Ingrid. Autonomous underwater grasping using a novel vision-based distance estimator Paper 7: Skaldebø, Martin Breivik; Schjølberg, Ingrid; Haugaløkken, Bent Oddvar Arnesen. Underwater Vehicle Manipulator System (UVMS) With BlueROV2 and SeaArm-2 Manipulator. I: ASME 2022 41st International Conference on Ocean, Offshore and Arctic Engineering Volume 5B: Ocean Engineering; Honoring Symposium for Professor Günther F. Clauss on Hydrodynamics and Ocean Engineering. Paper No: OMAE2022-79913, V05BT06A022; s. 1-8 https://doi.org/10.1115/OMAE2022-79913 Paper 8: Skaldebø, Martin Breivik; Schjølberg, Ingrid. Dynamic Bayesian Networks for Reduced Uncertainty in Underwater Operations. IFAC-PapersOnLine 2022 ;Volum 55. s. 409-414 https://doi.org/10.1016/j.ifacol.2022.10.462 This is an open access article under the CC BY-NC-ND license. Paper 9: Transeth, Aksel Andreas; Schjølberg, Ingrid; Lekkas, Anastasios M.; Risholm, Petter; Mohammed, Ahmed Kedir; Skaldebø, Martin Breivik; Haugaløkken, Bent Oddvar Arnesen; Bjerkeng, Magnus Christian; Tsiourva, Maria Efstathia; Py, Frédéric. Autonomous subsea intervention (SEAVENTION). 14th IFAC Conference on Control Applications in Marine Systems, Robotics and Vehicles (CAMS 2022) https://doi.org/10.1016/j.ifacol.2022.10.459 This is an open access article under the CC BY-NC-ND license Paper 10: Skaldebø, Martin Breivik; Schjølberg,Ingrid; Haugaløkken, Bent Oddvar Arnesen System integration of underwater vehicle manipulator system (UVMS) for autonomous grasping urn:isbn:978-82-326-5480-2 urn:issn:2703-8084 https://hdl.handle.net/11250/3047839 VDP::Technology: 500::Marine technology: 580 Doctoral thesis 2023 ftntnutrondheimi https://doi.org/10.1109/OCEANSE.2019.8867288 https://doi.org/10.23919/OCEANS40490.2019.8962583 https://doi.org/10.1016/j.robot.2020.103589 https://doi.org/10.23919/ECC54610.2021.9655121 https://doi.org/10.1109/JOE.2021.3126016 https://doi.org/10 2023-03-01T23:43:58Z This thesis considers intelligent solutions that facilitates for autonomous technology in underwater intervention and navigation. A special focus have been on implementing methods and solutions in inspection, maintenance, and repair (IMR) operations using low cost equipment. The presented work involves development and implementation of solutions to increase the efficiency and safety of operations, and includes both theoretical contributions and experimental testing. The work includes learning algorithms to improve visual authenticity of simulators and digital twin scenarios, computer vision in guidance and navigation of underwater vehicles and intervention systems, development and testing of novel equipment, and experimental verification of presented methods and equipment. The introduction of advanced learning algorithms enables systems to perform tasks that was previous too complex and complicated for any modelled solutions. This thesis explores the use of generative adversarial networks to improve the realism of simulated environments, which again will improve the transferred learning between simulated environments and real world operations. Such a mapping between domains is complex to model, especially in the underwater scene given the intricate scenery with scattering of light and marine particles. Machine learning algorithms provides new solutions for this mapping, and can aid in improving result from simulation tools to have greater impact on real world operations. In the same way humans uses their senses to experience life, autonomous systems requires sensory feedback to act and react upon. A sensor is only as effective as the information that can be extracted from the sensory output, and increasing and strengthening this information will improve the support from the sensor. Camera footage contain information with higher spatial and temporal resolution than acoustic information, and utilizing this information to its full will improve today's sensory systems. This thesis explores the use of visual aid and ... Doctoral or Postdoctoral Thesis Arctic NTNU Open Archive (Norwegian University of Science and Technology) OCEANS 2019 - Marseille 1 8 |