Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based Structures
The automation of typically intelligent and decision-making processes in the maritime industry leads to fewer accidents and more cost-effective operations. However, there are still lots of challenges to solve until fully autonomous systems can be employed. Artificial Intelligence (AI) has played a m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9393874/ |
| _version_ | 1818611395786178560 |
|---|---|
| author | Maria Ines Pereira Rafael Marques Claro Pedro Nuno Leite Andry Maykol Pinto |
| author_facet | Maria Ines Pereira Rafael Marques Claro Pedro Nuno Leite Andry Maykol Pinto |
| author_sort | Maria Ines Pereira |
| collection | DOAJ |
| description | The automation of typically intelligent and decision-making processes in the maritime industry leads to fewer accidents and more cost-effective operations. However, there are still lots of challenges to solve until fully autonomous systems can be employed. Artificial Intelligence (AI) has played a major role in this paradigm shift and shows great potential for solving some of these challenges, such as the docking process of an autonomous vessel. This work proposes a lightweight volumetric Convolutional Neural Network (vCNN) capable of recognizing different docking-based structures using 3D data in real-time. A synthetic-to-real domain adaptation approach is also proposed to accelerate the training process of the vCNN. This approach makes it possible to greatly decrease the cost of data acquisition and the need for advanced computational resources. Extensive experiments demonstrate an accuracy of over 90% in the recognition of different docking structures, using low resolution sensors. The inference time of the system was about 120ms on average. Results obtained using a real Autonomous Surface Vehicle (ASV) demonstrated that the vCNN trained with the synthetic-to-real domain adaptation approach is suitable for maritime mobile robots. This novel AI recognition method, combined with the utilization of 3D data, contributes to an increased robustness of the docking process regarding environmental constraints, such as rain and fog, as well as insufficient lighting in nighttime operations. |
| first_indexed | 2024-12-16T15:29:39Z |
| format | Article |
| id | doaj.art-347e8417b11049abbe275a525167abe3 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T15:29:39Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-347e8417b11049abbe275a525167abe32022-12-21T22:26:23ZengIEEEIEEE Access2169-35362021-01-019530305304510.1109/ACCESS.2021.30706949393874Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based StructuresMaria Ines Pereira0https://orcid.org/0000-0002-7796-3652Rafael Marques Claro1https://orcid.org/0000-0002-8010-7507Pedro Nuno Leite2https://orcid.org/0000-0002-9016-525XAndry Maykol Pinto3https://orcid.org/0000-0003-2465-5813Centre for Robotics and Autonomous Systems, INESC TEC, Porto, PortugalCentre for Robotics and Autonomous Systems, INESC TEC, Porto, PortugalCentre for Robotics and Autonomous Systems, INESC TEC, Porto, PortugalCentre for Robotics and Autonomous Systems, INESC TEC, Porto, PortugalThe automation of typically intelligent and decision-making processes in the maritime industry leads to fewer accidents and more cost-effective operations. However, there are still lots of challenges to solve until fully autonomous systems can be employed. Artificial Intelligence (AI) has played a major role in this paradigm shift and shows great potential for solving some of these challenges, such as the docking process of an autonomous vessel. This work proposes a lightweight volumetric Convolutional Neural Network (vCNN) capable of recognizing different docking-based structures using 3D data in real-time. A synthetic-to-real domain adaptation approach is also proposed to accelerate the training process of the vCNN. This approach makes it possible to greatly decrease the cost of data acquisition and the need for advanced computational resources. Extensive experiments demonstrate an accuracy of over 90% in the recognition of different docking structures, using low resolution sensors. The inference time of the system was about 120ms on average. Results obtained using a real Autonomous Surface Vehicle (ASV) demonstrated that the vCNN trained with the synthetic-to-real domain adaptation approach is suitable for maritime mobile robots. This novel AI recognition method, combined with the utilization of 3D data, contributes to an increased robustness of the docking process regarding environmental constraints, such as rain and fog, as well as insufficient lighting in nighttime operations.https://ieeexplore.ieee.org/document/9393874/Autonomous surface vehicledockingobject recognitionpoint cloud |
| spellingShingle | Maria Ines Pereira Rafael Marques Claro Pedro Nuno Leite Andry Maykol Pinto Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based Structures IEEE Access Autonomous surface vehicle docking object recognition point cloud |
| title | Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based Structures |
| title_full | Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based Structures |
| title_fullStr | Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based Structures |
| title_full_unstemmed | Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based Structures |
| title_short | Advancing Autonomous Surface Vehicles: A 3D Perception System for the Recognition and Assessment of Docking-Based Structures |
| title_sort | advancing autonomous surface vehicles a 3d perception system for the recognition and assessment of docking based structures |
| topic | Autonomous surface vehicle docking object recognition point cloud |
| url | https://ieeexplore.ieee.org/document/9393874/ |
| work_keys_str_mv | AT mariainespereira advancingautonomoussurfacevehiclesa3dperceptionsystemfortherecognitionandassessmentofdockingbasedstructures AT rafaelmarquesclaro advancingautonomoussurfacevehiclesa3dperceptionsystemfortherecognitionandassessmentofdockingbasedstructures AT pedronunoleite advancingautonomoussurfacevehiclesa3dperceptionsystemfortherecognitionandassessmentofdockingbasedstructures AT andrymaykolpinto advancingautonomoussurfacevehiclesa3dperceptionsystemfortherecognitionandassessmentofdockingbasedstructures |