Pasar al contenido principal

VALIDACION CIENTIFICA DE LA METODOLOGIA BASADA EN IA PARA LA EVALUACION Y RESTAURACION DE HABITATS MARINOS

AIA2025-163346-C44

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para la Investigación y el Desarrollo Experimental
Subprograma Subprograma Estatal de Generación de Conocimiento Científico-Técnico y Desarrollo Experimental
Convocatoria Proyectos de Investigación en el ámbito de la Inteligencia Artificial
Año convocatoria 2025
Plan Estatal 2024-2027 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario AGENCIA ESTATAL CONSEJO SUPERIOR DE INVESTIGACIONES CIENTIFICAS (CSIC)

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Rolling Locomotion for Shallow-Water Benthic Exploration Using a Compact Spherical Underwater Robot

  • Boiciuc, Costin
  • Picardi, Giacomo
  • Río, Joaquín del
  • Carandell, Matias
  • Toma, Daniel M.
7 pages, 7 figues, 2 tables.-- © 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, Shallow-water benthic environments require robotic platforms capable of operating with minimal ecological disturbance while maintaining reliable mobility and sensing. Conventional underwater vehicles typically rely on thrusters, which can resuspend sediment, increase turbidity, and introduce mechanical complexity through external moving parts and hull penetrations. This work presents a compact spherical underwater robot that achieves locomotion through internal eccentric-mass actuation, enabling a fully sealed architecture with no external propellers or mechanical penetrations, while external fins serve as the primary mechanism for effective propulsion through interaction with the surrounding fluid. The platform integrates a ROS 2-based embedded control and sensing system running on a Raspberry Pi 5, together with onboard inertial, electrical, and visual monitoring. Experimental validation was conducted at the water surface using multiple fin configurations and motor-speed conditions. Results show that fin geometry strongly influences both translational performance and dynamic stability. The nofin configuration provides the most stable response but limited traction, small fins offer the best compromise between controlled motion and effective rolling, and large fins maximize energy transfer at the cost of strong oscillatory instability at higher speeds. These findings demonstrate the feasibility of internally actuated rolling locomotion as a low-impact alternative for future benthic robotic platforms, The work was partially funded by the Spanish Ministry of Science, Innovation and Universities through the AI4SEA project (grant number AIA2025-163346-C4), This work contributes to the Institut de Ciències del Mar "Severo Ochoa Centre of Excellence" accreditation CEX2024-001494-S funded by AEI 10.13039/501100011033 of the Spanish Ministry of Science and Innovation, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

A review and case study on Underwater Legged Robot simulation

  • Aguirregomezcorta, Jorge
  • Aguzzi, Jacopo
  • Picardi, Giacomo
21 pages, 7 figures, 3 tables, appendixes, supplementary data https://doi.org/10.1016/j.oceaneng.2026.127084.-- Data availability: Source Code and Data for: A Review and Case Study on Underwater Legged Robot Simulation (Original data) (GitHub) https://github.com/joagai23/ulr_case_study, Underwater Legged Robots (ULRs) offer enhanced stability and precision for seabed mobility. However, translating these systems to real-world deployment requires high-fidelity virtual environments to develop and validate control and autonomy algorithms. To address this challenge, this research presents a comprehensive review of robotic simulators from the past decade. The analysis evaluates these platforms based on their hydrodynamics, seabed interaction, vehicle and sensor modeling, and Artificial Intelligence (AI) integration. Furthermore, it identifies critical gaps in the current state of the art that hinder the effective simulation of ULRs. Complementing this review, this paper benchmarks three simulation architectures through a unified hexapod ULR case study: the general-purpose Gazebo Sim, the marine-specific Stonefish, and the AI-driven NVIDIA Isaac Sim. To establish a consistent baseline for this comparison, a custom, GPU-accelerated hydrodynamics plugin was implemented within NVIDIA Isaac Sim to resolve its lack of baseline marine physics. The review reveals that current marine simulation platforms focus primarily on surface and water-column operations. Consequently, they often fail to integrate the multi-contact terrestrial mechanics and benthic hydrodynamics required for advanced ULR locomotion. The comparative analysis further demonstrates that, while framework selection ultimately depends on specific research objectives, successfully integrating multibody marine physics within parallelized architectures provides the computational foundation necessary to optimize AI-driven bio-inspired ULR locomotion, This work was supported by the European Union’s H2020 program through the DIGI4ECO, SUN-BIO, REDRESS, MERLIN, and TERRATWIN projects [grant numbers GAP-101112883, GAP-101157493, GAP-101135492, GAP-01189796, GAP-101214557]; the Spanish Ministry of Science and Innovation (MICINN) through the AI4SEA project [grant number AIA2025-163346-C44]; the Spanish Ministry of Environment through the SMART-ME project [grant number PID2024-1553440B-C31]; and the “la Caixa” Foundation [grant ID 100010434, fellowship code 161835]. [...] This work was developed within the framework of the Research Unit Tecnoterra (ICM-CSIC/UPC). This work also acknowledges the “Severo Ochoa Centre of Excellence” accreditation (CEX2019-000928-S), Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Datos de investigación Set de datos (Dataset)

A Review and Case Study on Underwater Legged Robot Simulation [Dataset]

  • Aguirregomezcorta, Jorge
  • Aguzzi, Jacopo
  • Picardi, Giacomo
Please follow the links below to access the specific implementation files, launch scripts, and documentation for each simulation framework evaluated in the study: 1. Gazebo Sim Implementation: Contains the ROS 2 integration and standard rigid-body simulation setup for the ULR within the general-purpose Gazebo Sim environment, utilizing community-developed marine extensions. 2. Stonefish Implementation: Contains the deployment of the ULR within the marine-specific Stonefish simulator, demonstrating the framework's native underwater capabilities and advanced hydrodynamics. 3. NVIDIA Isaac Sim & "Isaac Sea" Plugin: Contains the AI-driven simulation setup and the source code for Isaac Sea, our custom GPU-accelerated hydrodynamics plugin developed to bridge the gap between high-fidelity marine physics and large-scale parallelization for Deep Reinforcement Learning (DRL). 4. Data Analysis & Benchmarking Results (Local Directory): This directory contains the raw quantitative data and Jupyter notebooks used to generate the figures and tables presented in the manuscript. - Datasets (.csv): Includes aligned velocity metrics, drop test results, and computational resource measurements (RTF, GPU utilization, memory usage) for the terrestrial and hydrodynamic runs across all three simulators. - Notebooks (.ipynb): Python scripts detailing the data alignment, scaling factors, and visualization logic used to produce the velocity comparison and drop test plots for the manuscript, This repository serves as the central data and code hub for the manuscript "A review and case study on underwater legged robotics simulation," submitted to Ocean Engineering. To evaluate the transition from traditional Autonomous Underwater Vehicles (AUVs) to discrete, physical-contact Underwater Legged Robots (ULRs), this research benchmarks three distinct simulation architectures using a unified hexapod ULR case study (the SILVER2 platform). Due to the fundamental architectural differences between the tested frameworks, the source code, implementation details, and benchmarking data have been divided into three dedicated repositories, This work was supported by: The European Union’s H2020 program through the DIGI4ECO, SUN-BIO, REDRESS, MERLIN, and TERRATWIN projects [grant numbers GAP-101112883, GAP-101157493, GAP-101135492, GAP-01189796, GAP-101214557] The Spanish Ministry of Science and Innovation (MICINN) through the AI4SEA project [grant number AIA2025-163346-C44] The Spanish Ministry of Environment through the SMART-ME project [grant number PID2024-1553440B-C31] The ``la Caixa'' Foundation [grant ID 100010434, fellowship code 161835], This work contributes to the Institut de Ciències del Mar "Severo Ochoa Centre of Excellence" accreditation CEX2024-001494-S funded by AEI 10.13039/501100011033 of the Spanish Ministry of Science and Innovation, Peer reviewed