News – Vicorob

UdG Masters Students at RAMI 2025

ViCOROB — Mon, 14 Jul 2025 12:37:00 +0000

A team of international master’s students from the University of Girona has returned from Italy with strong results and valuable field experience after taking part in one of Europe’s most demanding underwater robotics competitions. Held at the NATO Centre for Maritime Research and Experimentation (CMRE) in La Spezia, the RAMI 2025 competition brought together academic teams from across the continent to test their autonomous underwater vehicles (AUVs) in real-world maritime scenarios. Participants were challenged to develop systems capable of subsea navigation, object detection, and intervention tasks typically required in offshore inspection and environmental monitoring operations.

Representing the Master in Intelligent Robotic Systems (MIRS) and the Erasmus Mundus Master in Intelligent Field Robotic Systems (IFRoS), the Girona team entered the competition with MiniGirona, an AUV designed and built within the framework of their master’s studies at the VICOROB research group and its Underwater Robotics Research Centre (CIRS).

Over the course of a week, the students worked alongside researchers and PhD from VICOROB to deploy, test, and refine the vehicle in a controlled but highly realistic maritime environment. The event provided a unique opportunity to apply academic knowledge to hands-on engineering tasks and team-based problem solving.

The team secured second place overall, in addition to receiving awards for Best Poster and Best Presentation. But beyond the rankings, the experience offered participants direct exposure to the complexity and pace of real-world marine robotics operations—a key step for those seeking careers in applied research and high-tech industries.

El CIRS inaugura una nova infrastructura

ViCOROB — Mon, 09 Jun 2025 12:33:57 +0000

El passat 6 de juny de 2025, varem celebrar un esdeveniment que marca un abans i un després en la recerca en robòtica submarina: la inauguració d’una nova piscina de proves. Aquesta infrastructura única al territori estatal suposa un salt qualitatiu per al nostre grup de recerca, consolidant la nostra capacitat per liderar projectes innovadors a escala nacional i internacional.

Amb cinc metres de profunditat, aquesta piscina incorpora tecnologia d’avantguarda: il·luminació subaquàtica, càmeres submergides i una sala d’observació amb finestres panoràmiques. Gràcies a aquestes característiques, podem recrear condicions marines en un entorn controlat, facilitant el desenvolupament i la validació de noves tecnologies abans del seu desplegament real. Aquest espai potenciarà projectes de recerca centrats en l’exploració i la preservació del medi marí, l’arqueologia submarina i les energies renovables.

Ha estat possible amb el suport i finançament per part del Ministeri de Ciència i Innovació i la Unió Europea, a través dels fons NextGenerationEU, dins del Pla de Recuperació, Transformació i Resiliència (PRTR).

Un punt clau d’aquesta jornada ha estat l’anunci sobre l’aspiració de convertir el CIRS en una Infraestructura Científica i Tècnica Singular (ICTS). Aquest reconeixement, atorgat pel Ministeri de Ciència i Innovació, posicionaria el nostre centre com una referència estatal i internacional, ampliant les oportunitats de col·laboració i accés a finçament per a projectes de recerca.

L’acte va comptar amb la presència de destacades autoritats, com el subdelegat del Govern espanyol a Girona, Pere Parramón i l’alcalde de Girona, Lluc Salellas. Durant els parlaments es va destacar la importància del nostre grup de recerca com a motor d’innovació i desenvolupament sostenible.

Premsa Online

06/06/2025

La UdG vol que el centre de robòtica submarina sigui una Infraestructura Científica i Tècnica Singular (ICTS). elpuntavui.cat

06/06/2025

UNIVERSITAT GIRONA | La UdG vol convertir el centre de robòtica submarina en una Infraestructura Científica i Tècnica Singular. diaridegirona.cat

06/06/2025

La UdG treballa per convertir el centre de robòtica submarina en una ICTS. El Gerió

06/06/2025

La UdG treballa per convertir el centre de robòtica submarina en una Infraestructura Científica i Tècnica Singular. lavanguardia.com

Advancing Underwater Robotics for Autonomous Assembly

ViCOROB — Wed, 14 May 2025 09:05:59 +0000

As part of the COOPERAMOS project, led by the University of Girona, research is being conducted to push the boundaries of underwater robotics. The COOPERAMOS project focuses on developing collaborative technologies for autonomous underwater vehicles (AUVs) to perform complex tasks, such as assembling structures beneath the sea.

In one of its experimental efforts, the University of Girona is exploring how these advanced robotic systems can autonomously assemble structures underwater—tasks that have traditionally depended on human-operated systems.

Underwater Assembly: From Vision to Reality
The current focus of the project is on assembling a structure made of multiple pipes, simulating tasks such as constructing underwater frameworks or infrastructure. This is being tested inside the CIRS water tank.
The Girona500 Intervention-AUV (I-AUV), equipped with two robotic arms is taking the lead. Using its arms, the vehicle can pick up and connect individual pipe sections, carefully aligning and inserting them to build larger assemblies.

A Glimpse into Cooperative Underwater Robotics
As the assembly grows longer and heavier, a key challenge arises: the structure becomes too large for a single robot to handle efficiently. At that point, a second robot will join the operation. Working together, the two robots will lift and stabilize the growing structure, allowing the dual-arm robot to continue the assembly process with precision and safety.
This approach will demonstrate how teams of underwater robots can dynamically adapt to the task, seamlessly shifting from solo operations to collaborative manipulation when needed.

Towards Safer, Smarter, and More Autonomous Ocean Missions
These experiments are paving the way for a future where autonomous robots can perform complex intervention tasks underwater, such as assembling parts of offshore infrastructure, maintaining underwater observatories, or supporting renewable energy installations.

https://vicorob.udg.edu/wp-content/uploads/2025/05/video_cooperamos.mp4

PLOME Project’s Breakthroughs

Neorg — Thu, 03 Aug 2023 09:50:09 +0000

The week of July 24 to 28, 2023, the first campaign at sea took place, more specifically in Cala del Vigatà in Sant Feliu de Guixols, where several of the project partners, in this case, UdG, UPM, Iqua and UPC carried out the first tests of the different developments of the project to verify the interoperability of the different hardware and software components.

The first activities took place at the CIRS, where the we and Iqua Robotics group have our facilities.

In summary, the objectives of the campaign were the verification of part of the electronic design, hardware and programming of the background stations, Landers, and surface proxy stations (UPC), the navigation of the Girona1000 underwater vehicle (UdG and Iqua Robotics) through its location referenced to the back-end stations and the development of firmware middleware (UPM) that implements the communications between the different devices and allows the interaction between them.

After the pool tests at CIRS (Girona), for the following days, the team moved to the port of Sant Feliu de Guixols, which would become the centre of operations for the rest of the campaign. From the port and employing two boats, the deployments of the bottom, surface and underwater robot equipment were carried out in Cala Vigatà to, in this case, carry out the tests in the open sea, in an environment much more similar to the final environment of the project, which are the marine protected areas (MPAs). Communications, file transfer, detection and geolocation tests of the vehicle’s background and navigation stations were carried out.

This milestone campaign not only propels marine technology but also underscores the PLOME project’s ambitions. To delve deeper into our journey and discoveries, visit the official PLOME Project website at https://plomeproject.es/.

Reinforcement learning allows underwater robots to locate and track objects underwater.

Neorg — Fri, 28 Jul 2023 08:44:15 +0000

Computer Vision and Robotics Research Group (UdG) is participating in this study led by the ICM-CSIC and published in the journal Science Robotics. The work demonstrates for the first time how a submarine robot is capable of learning the optimal trajectory to monitor the seabed and track species. The tests were conducted in Sant Feliu de Guíxols using autonomous underwater vehicles from VICOROB, and in California, using vehicles from the Bioinspiration Lab.

A team led by the Institute of Marine Sciences (ICM-CSIC) in Barcelona, in collaboration with the University of Girona (UdG), has demonstrated for the first time that deep reinforcement learning allows autonomous underwater vehicles and robots to locate and accurately track marine objects and animals underwater. Reinforcement learning is a neural network that learns the best action to take at each moment according to a series of rewards.

The details of this research are presented in a scientific article published in Science Robotics, the leading scientific journal in the field of robotics. The Monterey Bay Aquarium Research Institute (MBARI) in California and the Polytechnic University of Catalonia (UPC) have also participated in the study.

Currently, underwater robotics is becoming a key tool to improve knowledge of the oceans given the numerous challenges in exploring them, with vehicles capable of diving to depths of up to 4,000 meters. Furthermore, the in-situ data they provide helps complement other data sources, such as those obtained through satellites. This technology allows for the study of small-scale phenomena, such as the capture of CO2 by marine organisms, which contributes to regulating climate change.

Specifically, this new work reveals that reinforcement learning, widely used in control and robotics, as well as in the development of tools related to natural language processing like ChatGPT, enables underwater robots to learn the actions they should take at each moment to achieve a specific goal. These action policies equal or even outperform, under certain circumstances, traditional methods based on analytical development.

“This type of learning allows us to train a neural network to optimize a specific task, which would be very difficult to achieve otherwise. For example, we have demonstrated that it is possible to optimize the trajectory of a vehicle to locate and track objects moving underwater,” explains the study’s lead author, Ivan Masmitjà.

This “will allow us to delve into the study of ecological phenomena, such as migration or movement at small and large scales of many marine species, using autonomous robots. Additionally, these advancements will make it possible to supervise other oceanographic instruments in real-time through a network of robots, where some can be on the surface monitoring and transmitting the actions of other robotic platforms at the seafloor via satellite,” comments ICM-CSIC researcher Joan Navarro.

To carry out the study, the authors used the well-known “range acoustics techniques,” which estimate the position of an object based on distance measurements taken at different points. However, this fact makes the accuracy of object localization highly dependent on the location of the acoustic range measurements. This is where the application of artificial intelligence, specifically reinforcement learning, becomes crucial, as it identifies the best points and, consequently, the optimal trajectory for the robot to follow.

The neural networks were trained, in part, using the cluster of computers at the National Supercomputing Center of Barcelona, which houses the most powerful supercomputer in Spain and one of the most powerful in Europe. “This allowed us to adjust the parameters of different algorithms much faster than using conventional computers,” indicates Mario Martin, a co-author of the study and a professor in the Department of Computer Science at UPC.

Once trained, the algorithms were tested on different autonomous vehicles, including the AUV Sparus II developed by VICOROB, in a series of experimental missions conducted at the port of Sant Feliu de Guíxols and Monterey Bay (California), in collaboration with Kakani Katija, the principal investigator of the Bioinspiration Lab at MBARI.

“Our simulation environment incorporates the control architecture of real vehicles, which allowed us to effectively implement the algorithms before going to sea,” comments VICOROB researcher Narcís Palomeras.

For future research, the team will explore the possibility of applying the same algorithms to solve more complicated missions. For example, using multiple vehicles to locate objects, detect fronts and thermoclines, or cooperatively track algal blooms through multi-platform reinforcement learning techniques.

This research was carried out thanks to the prestigious European Marie Curie Individual Fellowship won by researcher Ivan Masmitjà in 2020 and the BITER project, funded by the Ministry of Science and Innovation of the Spanish Government, which is currently underway.

Reference article: Ivan Masmitjà, Mario Martin, Tom O’Reilly, Brian Kieft, Narcís Palomeras, Joan Navarro, and Kakani Katija (2023). Dynamic robotic tracking of underwater targets using Reinforcement Learning. Science Robotics, ade7811. DOI: 10.1126/scirobotics.ade7811.

Vicorob coordinates Two Erasmus Mundus Masters Programs in Robotics and Underwater Technologies

Neorg — Thu, 20 Apr 2023 14:17:05 +0000

Vicorob Research Group is coordinating two Erasmus Mundus masters programs, the MAIA Master in Medical Imaging and Applications and the IFROS Master in Intelligent Field Robotic Systems. These programs provide an incredible opportunity for students to study in multiple countries, access a diverse network of international students, and obtain a joint degree from multiple universities.

The MAIA Master focuses on computer vision and robotics, while the IFROS Master concentrates on underwater robotics and related technologies. Both programs offer an interdisciplinary curriculum that combines cutting-edge research with practical experience, giving students a unique opportunity to develop their skills in these rapidly-evolving fields.

To apply for the Erasmus Mundus masters programs, students must submit an online application and provide supporting materials, including academic transcripts, language proficiency scores, and letters of recommendation. The deadline for applications is usually in early January, but students are encouraged to check the program website for specific deadlines and requirements.

If you’re interested in applying for the MAIA Master or the IFROS Master, we encourage you to visit the program websites for more information. You can also contact the program coordinators directly for assistance with the application process or any other questions you may have.

Erasmus Mundus Master’s degree in Medical Imaging and Applications

Erasmus Mundus Master’s degree in Intelligent Field Robotic Systems

We look forward to welcoming a new cohort of talented students to our Erasmus Mundus masters programs!

VICOROB’s Research Recognized as Consolidated Group by AGAUR

Neorg — Fri, 10 Mar 2023 13:09:36 +0000

VICOROB research lines, Underwater Vision and Robotics, Medical Imaging, and Educational Robotics; have renewed their recognition as a consolidated research group from AGAUR, the Catalan Agency for the Management of University and Research Grants.

This recognition has a duration of 3 years, from 2022 to 2024, and we are very pleased to have obtained this renewal. The CIRS SGR and AIA SGR have also received funding to drive their research. The goal of the call is to boost the activities of the research groups to strengthen their scientific, economic, and social impact, as well as promote their international projection.

This recognition acknowledges the effort and work carried out in recent years and gives us a vote of confidence to continue at the level of excellence that we work towards every day in the following years.

Doctoral Thesis: Deep learning methods for extraction of neuroimage markers in the prognosis of brain pathologies

Neorg — Mon, 13 Feb 2023 09:00:35 +0000

By Albert Clèrigues Garcia

Supervised by Dr. Xavier Lladó / Dr. Arnau Oliver / Dr. Sergi Valverde

Abstract

This PhD thesis focuses on improving the extraction of neuroimage markers for the prognosis and outcome prediction of neurological pathologies such as ischemic stroke, Alzheimer’s disease (AD) and multiple sclerosis (MS). Our work has been developed on two of the most relevant neuroimage markers for diagnosis and prediction, brain lesion segmentation and longitudinal atrophy quantification. Brain lesion segmentation can be directly used in MS and ischemic stroke as a prognostic marker and can also be useful for other downstream segmentation tasks. In MS, disease activity produces very characteristic lesions which can help with diagnosis and prognosis of the pathology. In ischemic stroke, lesion segmentation can inform the treatment decision workflow by quantifying the amount of tissue that could be salvaged against the risks of surgical intervention. We also tackle in this PhD thesis the task of brain tissue segmentation for longitudinal atrophy quantification, a validated prognostic image marker in MS and AD. Measurements of longitudinal atrophy can be used to assess the rate of disease progression and might even help to predict AD onset years in advance. In MS patients, an accelerated rate of brain atrophy is also observed as a result of disease activity and is used as a prognostic marker and to evaluate the response of disease-modifying treatments.

The work in this thesis has been developed in several stages. In stage one, we approach the task of brain lesion segmentation and propose two patch-based deep learning methods for ischemic stroke, a 2D approach for computed tomography (CT) images and a 3D one for magnetic resonance imaging (MRI). Within both of these approaches, we have proposed training patch sampling techniques along with class balancing loss functions to mitigate the imbalance between healthy and lesion classes. We have also explored the use of several post-processing techniques to rectify the classification confidence of the model and filter lesions based on its morphology. Additionally, we have proposed a novel technique to exploit features based on the bilateral symmetry between brain hemispheres. The proposed approaches have shown state-of-the-art performance on two well-known publicly available datasets from the 2015 and 2018 editions of the Ischemic Stroke Lesion Segmentation (ISLES) challenge.

In the subsequent stages of this thesis, we focused on brain tissue segmentation for cross-sectional and longitudinal volumetric analysis. Although deep learning techniques have been at the forefront of many recent breakthroughs, current state- of-the-art methods for brain tissue segmentation have still not found a way to benefit from them. The main issue preventing their application is that the typically employed supervised deep learning methods would require accurate manual mea- surements of brain volumetry, which are virtually impossible to perform by human raters. Thus, we propose an unsupervised patch-based deep learning framework designed for accurate brain tissue segmentation which does not rely on manual annotations for training. Instead, we learn from the outputs of a reference classical segmentation method and use data-driven techniques to improve upon their results and compensate its shortcomings. This unsupervised brain tissue segmentation framework is used as the basis for the work performed in the next stages.

Although the effect of WM lesions typically observed in MS patient images has been extensively studied in classical brain tissue segmentation methods, it has still not been evaluated within the more recent deep learning based approaches. In this regard, we begin by studying and evaluating the error that is introduced by WM lesions in our deep learning based tissue segmentation framework. Then, we propose an approach to reduce the error that these lesions introduce in the measured tissue volumes. Typically, the gold standard technique to mitigate WM lesion effect is to perform a lesion filling or inpainting in a previous separate step to prevent the abnormal intensities from interfering with the tissue segmentation. Instead, we propose a data-driven technique that performs the inpainting and segmentation tasks in an end-to-end fashion within our deep learning framework. By jointly optimizing both tasks, we are able to obtain an inpainting model that is also trained to aid in the segmentation task and minimizes the WM lesion influence to almost negligible levels.

Finally, based on our previously developed unsupervised brain tissue segmen- tation framework, we propose a method for longitudinal atrophy quantification. Within our approach, the network learns from a reference tissue segmentation method while utilizing data priors to regularize the training and avoid learning its errors and biases. More specifically, we propose a tissue similarity regularization during training which penalizes volume differences between pairs of scans from the same patient made within a short time interval. The experimental results show our method has greatly reduced short interval error and improved sensitivity to differences between healthy and AD patients compared to the reference method used for training.

In this PhD thesis, we have worked with diverse neuroimage markers and imaging modalities, which has provided valuable insights on the issues and challenges for their use in prognostic and predictive tasks.

https://www.udg.edu/en/ed/tesis-doctorals/llista-de-tesis/codi/350130813

New project in breast cancer imaging

Neorg — Wed, 01 Feb 2023 13:11:29 +0000

Vicorob has secured a project funded by the Spanish Ministry of Science and Innovation. The project, titled “Virtual Clinical Trials and Pre-clinical Experiments for Optimizing New Imaging and AI Algorithms in Breast Cancer,” aims to advance breast cancer screening techniques.

Breast screening has had a significant impact in reducing mortality rates, with standard mammography being the most commonly used method. However, there is still room for improvement, especially in certain women populations, which can be achieved through emerging imaging modalities and computer aided diagnosis systems. These systems are based on deep learning and have shown comparable results to radiologists, but their robustness remains an issue.

The team behind the project is made up of experts from the University of Girona and Complutense University of Madrid in medical physics, radiology, artificial intelligence, software development, and computational genomics.

The goal of the project is to develop AI algorithms based on deep learning, machine learning, and image analysis to enhance the imaging and diagnosis processes of breast cancer.

The development of AI algorithms in the field of breast cancer screening has the potential to improve the accuracy and efficiency of diagnoses and ultimately save lives.

For more information on the project click here

VICOROB adds three new professorships

Neorg — Thu, 15 Dec 2022 10:49:31 +0000

Since the beginning of December VICOROB has three more professors in the group: Prof. Pere Ridao, Prof. Jordi Freixenet and Prof. Joan Martí. All three defended with brilliant presentations their opposition as full professors in the Computer Architecture and Technology Area of the Computer Architecture and Technology Department of the University of Girona.

The defenses took place on December 1st and 5th. In the different sessions, each of them explained their trajectory in management, teaching and research that have led them to obtain the position of professors.

Dr. Pere Ridao defended his research project on Underwater Robotics and Autonomous Underwater Vehicles, while Dr. Jordi Freixenet focused on the field of Machine and Creative Learning and Dr. Joan Martí on Computer Vision techniques in the diagnosis of breast cancer.

This recognition reaffirms the great teaching and research work done over the years and the leadership provided in their labs.

Currently VICOROB has a total of 7 researchers recognised as professors: Prof. Joan Batlle, Prof. Joaquim Salvi, Prof. Xavier Lladó, Prof. Rafael Garcia and the three latest incorporations Prof. Pere Ridao, Prof. Jordi Freixenet and Prof. Joan Martí.