Publications
An Unsupervised Neural Network for Loop Detection in Underwater Visual SLAM
On-Line Multi-Class Segmentation of Side-Scan Sonar Imagery Using an Autonomous Underwater Vehicle
This paper proposes a method to perform on-line multi-class segmentation of Side-Scan Sonar acoustic images, thus being able to build a semantic map of the sea bottom usable to search loop candidates in a SLAM context. The proposal follows three main steps. First, the...
Inter-Beat Interval Estimation from Extremely Noisy Single Lead Electrocardiograms
The advent of wearable recorders poses new challenges to electrocardiogram (ECG) analysis, such as robust feature extraction in front of long-term recordings with intervals of extreme noise. This paper proposes a robust approach to improve the estimates of one...
Visual Loop Detection in Underwater Robotics: An Unsupervised Deep Learning Approach
This paper presents a novel Deep Neural Network aimed at fast and robust visual loop detection targeted to underwater images. In order to help the proposed network to learn the features that define loop closings, a global image descriptor built upon clusters of local...
Clock Synchronization in Integrated TSN-EtherCAT Networks
Moving towards new technologies, such as Time Sensitive Networking (TSN), in industries should be gradual with a proper integration process instead of replacing the existing ones to make it beneficial in terms of cost and performance. Within this context, this paper...
Towards Multi-Robot Visual Graph-SLAM for Autonomous Marine Vehicles
An Architecture for Highly Reliable Fault-Tolerant Adaptive Distributed Embedded Systems
Critical Adaptive Distributed Embedded Systems (ADESs) will play a key role in future cyber-physical systems (CPSs), since there is an increasing demand for carrying out critical operations in unpredictable environments. A critical ADES must rely on a communication...
Comparing Admission Control Architectures for Real-Time Ethernet
Industry 4.0 and Autonomous Driving are emerging resource-intensive distributed application domains that deal with open and evolving environments. These systems are subject to stringent resource, timing, and other non-functional constraints, as well as frequent...
Towards Visual Loop Detection in Underwater Robotics using a Deep Neural Network
{This paper constitutes a first step towards the use of Deep Neural Networks to fast and robustly detect underwater visual loops. The proposed architecture is based on an autoencoder, replacing the decoder part by a set of fully connected layers. Thanks to that it is...
Segmentation through patch classification: A neural network approach to detect Posidonia oceanica in underwater images
This paper focuses on the detection of Posidonia oceanica in underwater images. The input image is split into a set of patches that are classified as depicting Posidonia or not. Two different Neural Networks are proposed to perform the classification. A region growing...
New Insights on Laser-based Structured Light for Underwater 3D Reconstruction
Uncertainty estimation for online seagrass semantic mapping using AUVs (Video)
(In construction) https://www.youtube.com/watch?v=c3FtvmufDvY&t=53s
Using Machine Learning and Heart Rate Variability Features to Predict Epileptic Seizures
This study constitutes a first step towards a wearable epileptic seizure prediction device. We exploit the existing correlation between epileptic pre-ictal states and heart rate variability features, since they can be measured by portable electrocardiogram recorders....
Design, Implementation and Validation of a System to Automatically Configure the Scheduling of Real-Time Traffic in Time Sensitive Networking (TSN) Switches
During the last years there is a growing interest in interconnecting and integrating systems that rely on InformationTechnologies (IT) with systems that rely on Operational Technologies (OT), i.e. on technologies used in industrial systems to monitor/control a plant....
Cluster-based Scan Matching for Robust Motion Estimation and Loop Closing
This paper presents a robust approach to estimate the relative motion between couples of range scans called CSoG. The algorithm first searches prominent structural features in one of the scans by means of a clustering algorithm. Thus, no assumptions about the...
Estudio de la idoneidad del Stream Reservation Protocol para dar soporte a Sistemas Empotrados Distribuidos Críticos Adaptativos
En 2005 el IEEE creó un Task Group con el objetivo de dotar a Ethernet de nuevos y mejores servicios de comunicaciones. Este grupo fue llamado Audio Video Bridging (AVB), y fue el responsable de proporcionar a Ethernet garantías de tiempo real suave a la vez que...
Marine Robots for IAS Control – Short
https://www.youtube.com/watch?v=c3FtvmufDvY This is the short version of the pitch video submitted to the Conservation X Lab Tech Prize, where we present Xiroi, an ASV able to automatically detect the invasive algae Halimeda incrassata.
Marine Robots for IAS Control
https://www.youtube.com/watch?v=FgharUfUAFM&t=53s This is the pitch video submitted to the Conservation X Lab Tech Prize, where we present Xiroi, an ASV able to automatically detect the invasive algae Halimeda incrassata.
Laser stripe bathymetry using particle filter SLAM
A deep learning solution for Posidonia oceanica seafloor habitat multiclass recognition
Recent studies have shown evidence of a significant decline of the Posidonia oceanica meadows on a global scale. The monitoring and mapping of these meadows and its marine habitat are fundamental tools for measuring its status and growth opportunities. The presence of...