Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

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

Miniaturised bidirectional acoustic tag to enhance marine animal tracking studies

  • Masmitja, Ivan
  • Corregidor, Daniel
  • López, Juan Manuel
  • Martínez, Enoc
  • Navarro, Joan
  • Gomáriz, Spartacus
IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 17-20 May 2021.-- 6 pages, 9 figures, 1 table, Acoustic underwater tags are key devices to study marine animals and comprehend their patterns, which provide essential behavioural information for applying new conservation policies. At present, all the acoustic tags have a unidirectional communication protocol, which introduces important limitations for their localisation such as range measurement, and in situ reconfiguration. To solve these issues and improve the current state-of-the-art acoustic tags, a new bidirectional tag device is presented in this paper. This innovative tag will allow new studies and will open a wide tracking capability by using autonomous underwater vehicles and range-based algorithms. Here, the main architecture of the tag, and its characteristics are presented alongside the first laboratory tests, and the results obtained, This work received financial support from different research projects of the Spanish Ministerio de Economía y Competitividad (SASES: RTI2018-095112-B-I00, RESNEP: CTM2017-82991-C2-1-R, and RESBIO: TEC2017-87861-R), of the Generalitat de Catalunya “Sistemas de Adquisición Remota de datos y Tratamiento de la Información en el Medio Marino (SARTI-MAR)” 2017 SGR 371. J. Navarro was funded by the Spanish National Program Ramón y Cajal (RYC-2015-17809). This project has also received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie - Individual Fellowship grant agreement AIforUTracking No 893089, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Analysis and initial design of bidirectional acoustic tag modulation schemes and communication protocol

  • Corregidor, Daniel
  • Masmitja, Ivan
  • López, Juan Manuel
  • Gomáriz, Spartacus
  • Navarro, Joan
  • Arcas Castro, Guillermo de
6 pages, 10 figures, 1 table, Acoustic underwater tags are key devices to study marine animals and obtain information regarding their behaviour. This information is essential to increase our knowledge of oceanic species and implement efficient conservation policies. At present, all the acoustic tags have a unidirectional communication protocol, which introduces important limitations for their localization such as range measurement, and in situ reconfiguration. To solve these issues and improve the current state-of-the-art of acoustic tags, a new bidirectional tag device has been developed. This new tag will allow new studies and will open a wide tracking capability by using autonomous underwater vehicles and range-based algorithms. The main characteristics of the tag communications scheme such as the chosen modulation, its implementation and the communication protocol are presented on this paper. Also, the simulation software and the conclusions that lead to the initial prototype design are presented, This work received financial support from the Spanish Ministerio de Economía y Competitividad (contract TEC2017-87861-R project RESBIO, RTI2018-095112-B-I00 project SASES, and CTM2017-82991-C2-1-R project RESNEP), from the Generalitat de Catalunya “Sistemas de Adquisición Remota de datos y Tratamiento de la Información en el Medio Marino (SARTI-MAR)” 2017 SGR 371. J. Navarro was funded by the Spanish National Program Ramón y Cajal (RYC-2015-17809). This project has also received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie - Individual Fellowship grant agreement AIforUTracking No 893089, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems

  • Gallici, Matteo
  • Martin, Mario
  • Masmitja, Ivan
International Conference on Autonomous Agents and Multiagent Systems (AAMAS '23), 29 May - 2 June 2023, London, United Kingdom.-- 9 pages, 6 figures, 1 table, supplementary material, Coordination is one of the most difficult aspects of multi-agent reinforcement learning (MARL). One reason is that agents normally choose their actions independently of one another. In order to see coordination strategies emerging from the combination of independent policies, the recent research has focused on the use of a centralized function (CF) that learns each agent's contribution to the team reward. However, the structure in which the environment is presented to the agents and to the CF is typically overlooked. We have observed that the features used to describe the coordination problem can be represented as vertex features of a latent graph structure. Here, we present TransfQMix, a new approach that uses transformers to leverage this latent structure and learn better coordination policies. Our transformer agents perform a graph reasoning over the state of the observable entities. Our transformer Q-mixer learns a monotonic mixing-function from a larger graph that includes the internal and external states of the agents. TransfQMix is designed to be entirely transferable, meaning that same parameters can be used to control and train larger or smaller teams of agents. This enables to deploy promising approaches to save training time and derive general policies in MARL, such as transfer learning, zero-shot transfer, and curriculum learning. We report TransfQMix's performances in the Spread and StarCraft II environments. In both settings, it outperforms state-of-the-art Q-Learning models, and it demonstrates effectiveness in solving problems that other methods can not solve, This project has received funding from the EU’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 893089. This work acknowledges the ‘Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000928-S), Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Platform-portable reinforcement learning methods to localize underwater targets

  • Masmitja, Ivan
  • Martin, Mario
  • O'Reilly, Tom
  • Palomeras, Narcís
  • Katija, Kakani
  • Navarro, Joan
OCEANS 2023, 05-08 June 2023, Limerick.-- 6 pages, 6 figures.-- © 20XX 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, 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, This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 893089. This work also received financial support from the Spanish Ministerio de Economía y Competitividad (BITERECO: PID2020-114732RB-C31). This work acknowledges the ’Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000928-S). We gratefully acknowledge the David and Lucile Packard Foundation, Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Otros (Other)

Engineering a testbed for bidirectional acoustic tag development

  • Batet, Gerard
  • Masmitja, Ivan
  • Sarriá, David
  • Gomáriz, Spartacus
  • Río, Joaquín del
OCEANS 2023, 05-08 June 2023, Limerick.-- 2 pages, 4 figures.-- © 2023 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, Marine protected areas (MPAs) have been implemented to mitigate the effects of climate change and overfishing on various marine ecosystems. Nonetheless, these areas need monitoring to ensure their actual utility. Tools like acoustic tags are used to study the animals’ behavioural patterns and obtain valuable information to improve MPAs. Recently, new architectures have been proposed to overcome the inherent limitations of off-the-shelf tags, for example, by implementing bidirectional communication capabilities with the newly developed open protocol from European Tracking Network. In this paper, the testbed topology and methodology used to develop these bidirectional acoustic tags are discussed alongside the laboratory results achieved, This work received financial support from different research projects of the Spanish Ministerio de Economía y Competitividad (SASES: RTI2018-095112-B-I00 and BITER: PID2020-114732RB-C32) and Generalitat de Catalunya’s “SARTI-MAR” 2017 SGR 371. IM received financial support from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie, grant agreement No 893089. GB received the support of Secretaria d’Universitats i Recerca del Departament d’Empresa i Coneixement de la Generalitat de Catalunya, With the institutional support of the ‘Severo Ochoa Centre of Excellence’ accreditation (CEX2019-000928-S), Peer reviewed