Detalhes
Nome
Pedro NunoCargo
Assistente de InvestigaçãoDesde
01 dezembro 2018
Nacionalidade
PortugalCentro
Centro de Robótica e Sistemas AutónomosContactos
+351222093233
pedro.nuno@inesctec.pt
2024
Autores
Mina, J; Leite, PN; Carvalho, J; Pinho, L; Gonçalves, EP; Pinto, AM;
Publicação
ROBOT 2023: SIXTH IBERIAN ROBOTICS CONFERENCE, VOL 2
Abstract
Underwater scenarios pose additional challenges to perception systems, as the collected imagery from sensors often suffers from limitations that hinder its practical usability. One crucial domain that relies on accurate underwater visibility assessment is underwater pipeline inspection. Manual assessment is impractical and time-consuming, emphasizing the need for automated algorithms. In this study, we focus on developing learning-based approaches to evaluate visibility in underwater environments. We explore various neural network architectures and evaluate them on data collected within real subsea scenarios. Notably, the ResNet18 model outperforms others, achieving a testing accuracy of 93.5% in visibility evaluation. In terms of inference time, the fastest model is MobileNetV3 Small, estimating a prediction within 42.45 ms. These findings represent significant progress in enabling unmanned marine operations and contribute to the advancement of autonomous underwater surveillance systems.
2024
Autores
Leite, PN; Pereira, PN; Dionisío, JMM; Pinto, AM;
Publicação
OCEAN ENGINEERING
Abstract
Offshore wind farms face harsh maritime conditions, prompting the use of sacrificial anodes to prevent rapid structural degradation. Regular maintenance and replacement of these elements are vital to ensure ongoing corrosion protection, maintain structural integrity, and optimize efficiency. This article details the design and validation of the MARESye hybrid underwater imaging system, capable of retrieving heterogeneous tri-dimensional information with millimetric precision for the close-range inspection of submerged critical structures. The optical prowess of the system is first validated during low turbidity trials where the volumetric properties of a decommissioned anode are reconstructed with absolute errors down to 0.0008 m, and its spatial dimensions are depicted with sub-millimeter precision accounting for relative errors as low as 0.31%. MARESye is later equipped as payload in a commercial ROV during areal environment inspection mission at the ATLANTIS Coastal Test Center. This experiment sees the sensor provide live reconstructions of a sacrificial anode, revealing a biofouling layer of approximately 0.0130 m thickness. The assessment of the high-fidelity 2D/3D information obtained from the MARESye sensor demonstrates its potential to enhance the situational awareness of underwater vehicles, fostering reliable O&M procedures.
2023
Autores
Dionisio, JMM; Pereira, PNAAS; Leite, PN; Neves, FS; Tavares, JMRS; Pinto, AM;
Publicação
OCEANS 2023 - LIMERICK
Abstract
Structures associated with offshore wind energy production require an arduous and cyclical inspection and maintenance (O&M) procedure. Moreover, the harsh challenges introduced by sub-sea phenomena hamper visibility, considerably affecting underwater missions. The lack of quality 3D information within these environments hinders the applicability of autonomous solutions in close-range navigation, fault inspection and intervention tasks since these have a very poor perception of the surrounding space. Deep learning techniques are widely used to solve these challenges in aerial scenarios. The developments in this subject are limited regarding underwater environments due to the lack of publicly disseminated underwater information. This article presents a new underwater dataset: NEREON, containing both 2D and 3D data gathered within real underwater environments at the ATLANTIS Coastal Test Centre. This dataset is adequate for monocular depth estimation tasks, which can provide useful information during O&M missions. With this in mind, a benchmark comparing different deep learning approaches in the literature was conducted and presented along with the NEREON dataset.
2021
Autores
Pereira, MI; Leite, PN; Pinto, AM;
Publicação
MARINE TECHNOLOGY SOCIETY JOURNAL
Abstract
The maritime industry has been following the paradigm shift toward the automation of typically intelligent procedures, with research regarding autonomous surface vehicles (ASVs) having seen an upward trend in recent years. However, this type of vehicle cannot be employed on a full scale until a few challenges are solved. For example, the docking process of an ASV is still a demanding task that currently requires human intervention. This research work proposes a volumetric convolutional neural network (vCNN) for the detection of docking structures from 3-D data, developed according to a balance between precision and speed. Another contribution of this article is a set of synthetically generated data regarding the context of docking structures. The dataset is composed of LiDAR point clouds, stereo images, GPS, and Inertial Measurement Unit (IMU) information. Several robustness tests carried out with different levels of Gaussian noise demonstrated an average accuracy of 93.34% and a deviation of 5.46% for the worst case. Furthermore, the system was fine-tuned and evaluated in a real commercial harbor, achieving an accuracy of over 96%. The developed classifier is able to detect different types of structures and works faster than other state-of-the-art methods that establish their performance in real environments.
2021
Autores
Pereira, MI; Claro, RM; Leite, PN; Pinto, AM;
Publicação
IEEE ACCESS
Abstract
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.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.