The Mini-Girona Intervention Autonomous Underwater Vehicle (I-AUV) represents an advancement in accessible underwater robotics, designed to bridge the gap between costly, specialized research AUVs and basic Remotely Operated Vehicles (ROVs). Developed with a focus on affordability and usability, the Mini-Girona, priced at approximately $50,000, integrates advanced components such as a 5-DOF manipulator arm, stereo vision, and AI-driven processing for autonomous navigation and intervention tasks. This paper presents the design and development of the Mini-Girona, detailing its performance during the RAMI 2025 student competition. Despite challenges such as thermal management issues and restricted team access, the Mini-Girona achieved second place overall, excelling in vision-based perception and intervention tasks. This work highlights the platform's potential as a tool for underwater robotics research and education, fostering innovation in real-world underwater applications.

Deep Reinforcement Learning (DRL) offers a robust alternative to traditional control methods for autonomous underwater docking, particularly in adapting to unpredictable environmental conditions. However, bridging the "sim-to-real" gap and managing high training latencies remain significant bottlenecks for practical deployment. This paper presents a systematic approach for autonomous docking using the Girona Autonomous Underwater Vehicle (AUV) by leveraging a high-fidelity digital twin environment. We adapted the Stonefish simulator into a multiprocessing RL framework to significantly accelerate the learning process while incorporating realistic AUV dynamics, collision models, and sensor noise. Using the Proximal Policy Optimization (PPO) algorithm, we developed a 6-DoF control policy trained in a headless environment with randomized starting positions to ensure generalized performance. Our reward structure accounts for distance, orientation, action smoothness, and adaptive collision penalties to facilitate soft docking. Experimental results demonstrate that the agent achieved a success rate of over 90

This work was developed under the need for an acoustic localization system to monitor marine protected areas (MPAs) with the help of autonomous underwater vehicles (AUVs). Although the use of acoustic signals for underwater localization has been previously studied, most of the solutions rely on filter-based optimization, which is prone to linearization problems in long-term applications. Instead, we implemented a Modular Acoustic Graph Simultaneous Localization and Mapping (SLAM) algorithm that, using a factor graph framework, tracks acoustic beacons with either ranges or bearings. In addition, we developed several novel methods, like a delayed-position update for ultra-short baseline (USBL) position factor integration process, an initialization algorithm for acoustic landmarks, and the creation of a new 3D bearing factor that combines two angles. After developing the algorithm, field experiments were carried out in different areas on the coast of Catalonia. Besides the localization, some monitoring tasks were also tested, such as visual mapping of localized landmarks or optical transmission of data with seafloor stations, which helped validate the accuracy of the acoustic localization system. The results of such experiments are presented and discussed.

A way to assess the effectiveness of marine protected areas (MPAs) is to study and analyze the fauna dynamics within them. To do so, an option is to attach acoustic pingers to some specimens and track their movement within an interval of time. Such analysis cannot be limited to presence detection, but instead requires fine-scale tracking, which can be challenging due to the specimens' unknown distribution, as well as the pingers' noisy and low-rate signals. These requirements and challenges render traditional approaches that use preplanned survey trajectories insufficient, thus requiring adaptable strategies such as informative path planning (IPP), which can adjust the trajectories based on the information obtained while conducting the survey. Most existing IPP strategies rely on continuous sensor data to replan the trajectories. However, due to the acoustic signal sparsity, these strategies cannot be applied in our case. Therefore, in this work, we propose a novel observability-based IPP approach that maps the specimens in a 3D space using an autonomous underwater vehicle (AUV), while also localizing several specimens simultaneously. We validate our approach with both an extensive simulation benchmark that considers different plausible arrangements of the benthic fauna, plus various experiments at sea. The results demonstrate that our approach enables the localization and mapping of the specimens within a specified uncertainty.

The implementation of Marine Protected Areas (MPAs) has increased in the last few decades, creating a deep impact on ocean governance and local fishery communities. Despite their effectiveness being actively debated, initial results show that this spatial management could promote the recovery of depleted marine communities and species, and ecosystem services such as increased fishing profits, especially in nearby areas. This could potentially maintain the economic levels of local and regional under-pressure economies while improving the overall marine biodiversity. However, the lack of ecological monitoring systems for long-lasting, non-invasive, and multiparametric measurements in near-real-time is a roadblock to national-level monitoring programs in those areas. Here we present a set of technological solutions, including robotics, biologging, and machine learning approaches to monitor MPAs, developed and validated in different deep-sea field experiments. The outcomes of these trials have yielded insights into the fine-scale behavioral ecology of different deep-sea species and the recovery dynamics of overexploited seafloors. With these tools, it is possible to monitor restored areas via ecological indicators, that are key to informing and empowering policymakers, conservation biologists, and fishery ecology experts, propelling an effective approach to the conservation and governance of marine ecosystems.

Robot localization is a fundamental task in achieving true autonomy. Recently, many graph-based navigators have been proposed that combine an inertial measurement unit (IMU) with an exteroceptive sensor applying IMU preintegration to synchronize both sensors. IMUs are affected by biases that also have to be estimated. To increase the navigator robustness when faults appear on the perception system, IMU preintegration can be complemented with linear velocity measurements obtained from visual odometry, leg odometry, or a Doppler Velocity Log (DVL), depending on the robotic application. Moreover, higher grade IMUs are sensitive to the Earth rotation rate, which must be compensated in the preintegrated measurements. In this article, we propose a general purpose preintegration methodology formulated on a compact Lie group to set motion constraints on graph simultaneous localization and mapping problems considering the Earth rotation effect. We introduce the SEN(3) group to jointly preintegrate IMU data and linear velocity measurements to preserve all the existing correlation within the preintegrated quantity. Field experiments using an autonomous underwater vehicle equipped with a DVL and a navigational grade IMU are provided and results are benchmarked against a commercial filter-based inertial navigation system to prove the effectiveness of our methodology.

By fusing a MultiBeam EchoSounder (MBES) with an Inertial Measurement Unit (IMU) and a Doppler Velocity Log (DVL) we present MINS: a graph-based, tightly coupled, and featureless MBES-Inertial Navigation System that enables accurate and real-time robot trajectory estimation, map building, and sensor bias estimation. MINS formulates an MBES-Inertial odometry problem for an Autonomous Underwater Vehicle (AUV) using a factor graph. The relative displacement estimated from the joint IMU and DVL preintegration is used to chain keyframes and to build 3D scans from a Mechanical Scanning MBES. This sensor allows the AUV to be immersed within the inspected scene to build a 3D point cloud map — which we call 3D bathymetry — compared to conventional systems that use an AUV navigating above the inspected area to collect a 2.5D bathymetry. The obtained scans are aligned to set sonar odometry or loop closure factors, by applying a probabilistic registration algorithm that uses Gaussian Mixture Models to represent the scans and quantify the alignment uncertainty. A rigorous on-manifold formulation is provided, which properly models the AUV state uncertainty in a compact Lie group. This system is evaluated in a field experiment demonstrating its ability to produce an accurate and consistent 3D bathymetry of a shipwreck.

In robotics, occupancy grids serve as required repositories of information about the environment in numerous applications. One such critical application is Simultaneous Localization and Mapping (SLAM), where robots dynamically scan and explore their surroundings while in motion. In the context of extended-duration missions, it becomes imperative to confront the complexities linked to the expansion of occupancy grids as well as handling loop closure detection. These challenges primarily revolve around two key aspects: enabling the seamless expansion of the map on multiple occasions, thus avoiding the need to map smaller regions in numerous separate missions, and ensuring real-time updates to the map to sustain the robot's knowledge base and enhance its responsiveness. To address these challenges, we introduce an innovative map called Frustum Accelerated GPU-Based Grid Map (FRAGG-Map). This map adopts a highly parallelizable 3D grid structure and leverages the power of CUDA kernels to facilitate efficient insertion of point-clouds and enables real-time updates of the map. FRAGG-Map identifies the portions of the map that require updates and utilises the GPU to update them, significantly enhancing computational performance. Our results show that FRAGG-Map can run 31 times faster than OctoMap, significantly outperforming state-of-the-art methods.

The underwater domain is a challenging environment for robotics because widely used electromagnetic devices must be substituted by acoustic equivalents, much slower and noisier. In this paper a two-dimensional pose simultaneous localization and mapping (SLAM) system for an Autonomous Underwater Vehicle based on inertial sensors and a mechanical profiling sonar is presented. Two main systems are specially designed. On the one hand, a dead reckoning system based on Lie Theory is presented to track integrated pose uncertainty. On the other hand, a rigid scan matching technique specialized for acoustic data is proposed, which allows one to estimate the uncertainty of the matching result. Moreover, Bayesian-Gaussian mixtures models are introduced to the scan matching problem and the registration problem is solved by an optimization in Lie groups. The SLAM system is tested on real data and executed in real time with the robotic application. Using this system, section maps at constant depth can be obtained from a three-dimensional underwater domain. The presented SLAM system constitutes the first achievement towards an underwater Active SLAM application.

This paper addresses the challenge of docking an Autonomous Underwater Vehicle (AUV) under realistic conditions. Traditional model-based controllers are often constrained by the complexity and variability of the ocean environment. To overcome these limitations, we propose a Deep Reinforcement Learning (DRL) approach to manage the homing and docking maneuver. First, we define the proposed docking task in terms of its observations, actions, and reward function, aiming to bridge the gap between theoretical DRL research and docking algorithms tested on real vehicles. Additionally, we introduce a novel observation space that combines raw noisy observations with filtered data obtained using an Extended Kalman Filter (EKF). We demonstrate the effectiveness of this approach through simulations with various DRL algorithms, showing that the proposed observations can produce stable policies in fewer learning steps, outperforming not only traditional control methods but also policies obtained by the same DRL algorithms in noise-free environments.

This paper presents a novel algorithm to dock a non-holonomic Autonomous Underwater Vehicle (AUV) into a funnel-shaped Docking Station (DS), in the presence of ocean currents. In a previous work, the authors have compared several docking algorithms through Monte Carlo simulations. In this paper, a new control algorithm is presented with a goal to improve over the previous ones to fulfil the specific needs of the ATLANTIS project. Performance of the new proposed algorithm has been compared with the results of the previous study, using the same environemnt on the Stonefish hardware-in-the-loop simulator.

Few advancements in underwater species tracking have occurred in recent years. For instance, acoustic biotelemetry systems were initially employed in the late '70s, and since then, only minimum improvements have been made in terms of range and battery life. The development of a bidirectional acoustic tag, combined with other technologies such as autonomous surface and underwater vehicles, promises a significant leap forward in the field, offering enhanced data precision at a reduced operational cost. This work presents the first tests and their setup for understanding AUV compatibility with commercial and novel bidirectional tags alongside the results.

Current acoustic localization systems for Autonomous Underwater Vehicles (AUV) rely on acoustic beacons at known positions. We present a method that combines rangeonly acoustic measures and odometry data into a factor graph structure, able to compute the AUV localization while estimating the position of the acoustic beacons without having previous information about their position. We designed several missions and carried them out in a real environment to gather data to test our algorithm offline. The output of this work is a pose-graph SLAM algorithm that combines the AUV internal measurements (i.e. DVL, IMU, and depth) with acoustic ranges from static beacons to estimate both the AUV state and the beacon’s position.

To realize the potential of autonomous underwater robots that scale up our observational capacity in the ocean, new techniques are needed. Fleets of autonomous robots could be used to study complex marine systems and animals with either new imaging configurations or by tracking tagged animals to study their behavior. These activities can then inform and create new policies for community conservation. The role of animal connectivity via active movement of animals represents a major knowledge gap related to the distribution of deep ocean populations. Tracking underwater targets represents a major challenge for observing biological processes in situ, and methods to robustly respond to a changing environment during monitoring missions are needed. Analytical techniques for optimal sensor placement and path planning to locate underwater targets are not straightforward in such cases. The aim of this study was to investigate the use of reinforcement learning as a tool for range-only underwater target-tracking optimization, whose promising capabilities have been demonstrated in terrestrial scenarios. To evaluate its usefulness, a reinforcement learning method was implemented as a path planning system for an autonomous surface vehicle while tracking an underwater mobile target. A complete description of an open-source model, performance metrics in simulated environments, and evaluated algorithms based on more than 15 hours of at-sea field experiments are presented. These efforts demonstrate that deep reinforcement learning is a powerful approach that enhances the abilities of autonomous robots in the ocean and encourages the deployment of algorithms like these for monitoring marine biological systems in the future.

Robot localization is a fundamental task in achieving true autonomy for Autonomous Underwater Vehicles (AUV). If inertial measurements from an Inertial Measurement Unit (IMU) or a Doppler Velocity Log (DVL) want to be fused with some perception system, such us a multibeam sonar or several acoustic beacons; a full Simultaneous Localization And Mapping (SLAM) problem must be solved. In contrast to filters, in a full SLAM problem the whole robot trajectory is estimated and loop closure events can be detected and closed along it. Common Inertial Navigation Systems (INS), based on filters, only maintain the estimation of the current robot pose. Therefore, these systems cannot be directly used in a full SLAM problem. In this paper we present a graph solution to integrate all inertial measurements in a factor graph that can be extended to different perception modalities and it is solved by applying Smoothing and Mapping (SAM) [1]. The Preintegrated IMU factor, proposed by [2], is combined with priors for other inertial measurements that have been specially designed. This framework is tested on real data from sea experiments, showing how our proposal performance is similar to the estimation provided by high grade commercial INS products based on filters. However, our system has the advantage of allowing for fusion with exteroceptive sensors in SLAM.

Subsea residential autonomous systems will reduce the cost and CO 2 footprint of future subsea operations. This concept includes subsea docking stations (SDS) and Autonomous Underwater Vehicles (AUVs). To ensure the AUVs are capable of interfacing with the SDS, a driftless and accurate close-range navigation schema is required. Thus, this paper proposes a visual method for navigation utilizing a defined set of ArUco markers printed on the SDS. To increase the accuracy of the system, the set of ArUco markers is defined to a common frame of reference, introducing more points in the camera frame for a more accurate solution to the Perspective-n-Point problem. This makes the system robust against partial occlusion. The paper has also implemented a modified Line of Sight (LOS) schema for the guidance of the vehicle. The results show stable pose estimates at up to 6 meters above the SDS, and successful autonomous docking of an underwater vehicle. The navigational estimates provided by the system get more stable when the vehicle is closer to the SDS.

Acoustic perception in underwater environments is challenging due to the low frequency of the acquisition system and multiple and huge sources of noise. Therefore, point clouds built by profiling sonars mounted on Autonomous Underwater Vehicles (AUV) are sparse and noisy. To solve the mapping task, AUVs need a registration algorithm to prevent maps from inconsistencies. Many scan matching algorithms are available, however, a few of them are specialized in acoustic data. In this paper, a probabilistic scan matching methodology based on Gaussian Mixtures Models (GMM) is presented and, for the first time, the Bayesian-GMM algorithm is applied in this context to model acoustic data. The scan matching problem is properly formulated using Lie groups to define pose. In addition, this methodology can return an uncertainty measure for the matching result, which is fundamental in Pose SLAM applications. This tool is implemented in a public C++library 1 1 The library repository can be found in https://bitbucket.org/gmmregistration/gmm_registration. that can process in real-time 2D and 3D scans acquired by a profiling sonar. Theoretical justification and results with real data are provided to benchmark our method against the state-of-the-art Normal Distributions Transforms (NDT) technique.

OPTIHROV is a proof-of-concept project to demonstrate a telerobotic system, based on an untethered, OPTIcally-connected, Hybrid Autonomous-ROV, that aims to replace light intervention ROVs operating at close range to networked infrastructures. The system is designed to bridge the gap between current ROVs, tethered to a Docking Station, and the dream of the future Intervention Autonomous Underwater Vehicle (I-AUV). OPTIHROV is a telerobotic system to perform inspection and light intervention tasks in potentially unknown and unstructured environments. It uses human-robot interaction (HRI) methods that allow the user to remotely guide the robot by launching a set of sensory-motion primitives performed by the robot autonomously.This paper presents a proof of concept demonstration of the OPTIHROV concept, where the wireless Hybrid Remotely Operated Vehicle (HROV), located in the test tank of the Universitat de Girona (UdG), is controlled/supervised from the Universitat Jaume I (UJI) in Castelló de la Plana, about 330 km away.

Offshore wind farms are a crucial source of renewable energy, but maintenance and repair can be challenging due to their remote locations and harsh environmental conditions. Professional divers or Remotely Operated Vehicles (ROVs) are commonly used to conduct maintenance operations, but they come with high daily operational costs. Autonomous Underwater Vehicles (AUVs) have the potential to improve the efficiency, safety, and costs of maintenance operations. This project evaluates the feasibility of using an AUV to conduct a cathodic protection (CP) survey, which involves measuring the corrosion potential of underwater structures to prevent deterioration. The AUV is equipped with a manipulator that has a CP probe with a sharp tip to puncture through the structure’s coating and make contact with the steel underneath. To ensure high accuracy and reduce environmental perturbances, the AUV attaches to the structure while conducting the survey. The technology and methods used in this project are demonstrated in a water tank using a Girona1000 AUV. Task Priority kinematic control is combined with a custom force control strategy based on admittance control to enable tracking of the end-effector configuration and contact force during the probing operation. The mission flow control is implemented using behavior trees. The results show that the use of AUVs for CP surveys is feasible and has the potential to significantly improve the efficiency, safety, and costs of maintenance operations in offshore wind farms.

The Norway lobster, Nephrops norvegicus, supports a key European fishery. Stock assessments for this species are mostly based on trawling and UnderWater TeleVision (UWTV) surveys. However, N. norvegicus are burrowing organisms and these survey methods are unable to sample or observe individuals in their burrows. To account for this, UWTV surveys generally assume that "1 burrow system = 1 animal", due to the territorial behavior of N. norvegicus. Nevertheless, this assumption still requires in-situ validation. Here, we outline how to improve the accuracy of current stock assessments for N. norvegicus with novel ecological monitoring technologies, including: robotic fixed and mobile camera-platforms, telemetry, environmental DNA (eDNA), and Artificial Intelligence (AI). First, we outline the present status and threat for overexploitation in N. norvegicus stocks. Then, we discuss how the burrowing behavior of N. norvegicus biases current stock assessment methods. We propose that state-of-the-art stationary and mobile robotic platforms endowed with innovative sensors and complemented with AI tools could be used to count both animals and burrows systems in-situ, as well as to provide key insights into burrowing behavior. Next, we illustrate how multiparametric monitoring can be incorporated into assessments of physiology and burrowing behavior. Finally, we develop a flowchart for the appropriate treatment of multiparametric biological and environmental data required to improve current stock assessment methods.