Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments

  • Dopico Castro, Alejandro
  • Fontenla-Romero, Óscar
  • Guijarro-Berdiñas, Bertha
  • Alonso-Betanzos, Amparo
  • Pérez Digón, Iván
[Abstract]: Federated Learning (FL) enables collaborative training without centralizing data, essential for privacy compliance in real-world scenarios involving sensitive visual information. Most FL approaches rely on expensive, iterative deep network optimization, which still risks privacy via shared gradients. In this work, we propose FedHENet, extending the FedHEONN framework to image classification. By using a fixed, pretrained feature extractor and learning only a single output layer, we avoid costly local fine-tuning. This layer is learned by analytically aggregating client knowledge in a single round of communication using homomorphic encryption (HE). Experiments show that FedHENet achieves competitive accuracy compared to iterative FL baselines while demonstrating superior stability performance and up to 70% better energy efficiency. Crucially, our method is hyperparameter-free, removing the carbon footprint associated with hyperparameter tuning in standard FL. Code available in https://github.com/AlejandroDopico2/FedHENet/, Work funded by Project PID2023-147404OB-I00 (MICIU/AEI/10.13039/501100011033; ERDF/EU; ESF+/EU), Horizon Europe (GA 101070381), and the Ministry for Digital Transformation and Civil Service and Next-GenerationEU/PRTR (TSI-100925-2023-1). CITIC, as a member of the CIGUS Network, receives subsidies from the “Xunta de Galicia” and from the ERDF Operational Programme Galicia 2021-2027 (Grant ED431G 2023/01), Xunta de Galicia; ED431G 2023/01
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Autonomous Generation of Sub-goals for Lifelong Learning in Robots

  • Fallas Hernández, Emanuel
  • Martínez-Alonso, Sergio
  • Romero, Alejandro
  • Becerra Permuy, José Antonio
  • Duro, Richard J.
The conference was held in Rome, Italy, from 30 June to 5 July 2025., [Abstract]: One of the challenges of open-ended learning in robots is the need to autonomously discover goals and learn skills to achieve them. However, when in lifelong learning settings, it is always desirable to generate sub-goals with their associated skills, without relying on explicit reward, as steppingstones to a goal. This allows sub-goals and skills to be reused to facilitate achieving other goals. This work proposes a two-pronged approach for sub-goal generation to address this challenge: a top-down approach, where sub-goals are hierarchically derived from general goals using intrinsic motivations to discover them, and a bottom-up approach, where sub-goal chains emerge from making latent relationships between goals and perceptual classes that were previously learned in different domains explicit. These methods help the robot to autonomously generate and chain sub-goals as a way to achieve more general goals. Additionally, they create more abstract representations of goals, helping to reduce sub-goal duplication and make the learning of skills more efficient. Implemented within an existing cognitive architecture for lifelong open-ended learning and tested with a real robot, our approach enhances the robot’s ability to discover and achieve goals, generate sub-goals in an efficient manner, generalize learned skills, and operate in dynamic and unknown environments without explicit intermediate rewards., This work was funded by the European Union’s Horizon 2020, research and innovation programme under GA 101070381 (PILLAR-Robots - Purposeful Intrinsically-motivated Lifelong Learning Autonomous Robots’), by Xunta de Galicia (EDC431C-2021/39), by the Spanish Science and Education Ministry (PID2021-126220OB-I00), and the Ministry for Digital Transformation and Civil Service and Next-Generation EU/RRF (TSI-100925-2023-1), by “ERDF A way of making Europe”, and Centro de Investigacion de Galicia “CITIC” (ED431G 2019/01)., Xunta de Galicia; EDC431C-2021/39, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Guiding the Exploration of the Solution Space in Walking Robots Through Growth-Based Morphological Development

  • Naya-Varela, M.
  • Duro, Richard J.
  • Faíña, Andrés
This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '23). Association for Computing Machinery, New York, NY, USA, 1230–1238. https://doi.org/10.1145/3583131.3590489., Included in: GECCO '23: Genetic and Evolutionary Computation Conference, Lisbon, Portugal July 15-19, 2023., [Abstract]: In human beings, the joint development of the body and cognitive system has been shown to facilitate the acquisition of new skills and abilities. In the literature, these natural principles have been applied to robotics with mixed results and different authors have suggested several hypotheses to explain them. One of the most popular hypotheses states that morphological development improves learning by increasing exploration of the solution space, avoiding stagnation in local optima. In this article, we are going to study the influence of growth-based morphological development and its nuances as a tool to improve the exploration of the solution space. We will perform a series of experiments over two different robot morphologies which learn to walk. Furthermore, we will compare these results to another optimization strategy that has been shown to be useful to favor exploration in learning algorithms: the application of noise during learning. Finally, to check if the increased exploration hypothesis holds, we visualize the genotypic space during learning considering the different optimization strategies by using the Search Trajectory Network representation. The results indicate that noise and growth increase exploration, but only growth guides the search towards good solutions., Research supported by the European Commission Horizon program PILLAR-Robots project, grant 101070381, the Xunta de Galicia and the European Regional Development Funds under grant EDC431C-2021/39, the Spanish Science and Education Ministry through grant PID2021-126220OB-100. M. Naya-Varela wish to acknowledge the support received by the Xunta de Galicia with his grant ED481B. We wish to acknowledge the support received from the Centro de Investigación "CITIC", funded by Xunta de Galicia and the European Union (European Regional Development Fund- Galicia 2014-2020 Program), by grant ED431G 2019/01 and the Centro de Supercomputación de Galicia (CESGA)., Xunta de Galicia; EDC431C-2021/39, Xunta de Galicia; ED481B, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Learning Multiple Tasks with Non-stationary Interdependencies in Autonomous Robots

  • Romero, Alejandro
  • Baldassarre, Gianluca
  • Duro, Richard J.
  • Santucci, Vieri Giuliano
[Abstract] An important challenge in the field of autonomous open-ended learning is the autonomous learning of interdependent tasks, and in particular when such interdependencies are non-stationary, so that the robot has to modify the acquired knowledge to properly sequence goals that constitute preconditions for other ones. This work proposes a hierarchical robotic architecture to address this type of scenarios, allowing for the autonomous learning of both the skills necessary to achieve the multiple goals, and of the sequences reflecting the relations between them. Moreover, our system is endowed with a mechanism that, on the basis of self-estimated competence over goal achievement, is able to self-tune the exploration-exploitation balance to cope with the non-stationarity of the environment. The architecture is tested using an UR5e robot operating in a scenario where it should autonomously learn to accomplish various manipulation tasks., This work was partially supported by the MCIU of Spain/FEDER (grant RTI2018-101114-B-I00), Xunta de Galicia (EDC431C-2021/39), Centro de Investigación de Galicia "CITIC" (ED431G 2019/01), and partially by the European Union’s Horizon 2020 Research and Innovation Programme under GA no 713010 (‘GOAL-Robots – Goalbased Open-ended Autonomous Learning Robots’) and GA 945539 (‘Human Brain Project, BP SGA3’), and partially by Horizon Europe, GA 101070381 (‘PILLAR-Robots - Purposeful Intrinsically motivated Lifelong Learning Autonomous Robots’)., Xunta de Galicia; EDC431C-2021/39, Xunta de Galicia; ED431G 2019/01
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Autonomous Discovery and Learning of Interdependent Goals in Non-Stationary Scenarios

  • Romero, Alejandro
  • Baldassarre, Gianluca
  • Duro, Richard J.
  • Santucci, Vieri Giuliano
Manuscrito aceptado, [Abstract] Developing artificial agents able to autonomously discover interesting states of the environment, set them as goals and learn the related skills and curricula is a paramount challenge for the deployment of robotic systems in real-world scenarios. Here robots must adapt to situations not foreseen at design-time and learn new skills eventually handling unexpected changes in the environment. In this work we present and test a cognitive architecture for robotic control, that integrates different features and mechanisms in a developmental perspective. In particular, we propose to treat goal-discovery as a specific motivation and allow the system to autonomously select it through a motivation selector. Moreover, we also propose to use intrinsic motivations (specifically the measure of competence) to let the system autonomously regulate its exploration in the learning of curricula of interrelated goals. The presented robotic experiments show the advantages of our approach in learning to achieve different goals with non-stationary interdependencies., This work was partially funded by MCIN/AEI/10.13039/501100011033 (PID2021-126220OB-I00), and by “ERDF A way of making Europe”, Xunta de Galicia (EDC431C-2021/39), Centro de Investigación de Galicia “CITIC” (ED431G 2019/01), and by the European Union’s Horizon 2020, research and innovation programme under GA 101070381 (‘PILLAR-Robots - Purposeful Intrinsically-motivated Lifelong Learning Autonomous Robots’)., Xunta de Galicia; ED431G 2019/01, Xunta de Galicia; EDC431C-2021/39
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Learning Adaptable Utility Models for Morphological Diversity

  • Campos-Alfaro, Francella
  • Jara, Carlos
  • Romero, Alejandro
  • Naya-Varela, M.
  • Duro, Richard J.
This version of the conference paper has been accepted for publication, after peer review and is subject to Springer Nature’s AM terms of use (https://www.springernature.com/gp/open-science/policies/accepted-manuscript-terms), but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-61137-7_11., [Abstract]: This paper introduces an approach to the integration of open-ended learning in modular robotics. We aim to provide these robots, equipped with morphological adaptability, with the capability to autonomously learn utility models specific to each morphology, discovering objectives on their own through a motivational system designed for open-ended learning. This system incorporates intrinsic motivations based on novelty and introduces a unique intrinsic motivation based on frustration to prevent learning stagnation. Furthermore, the paper addresses the autonomous learning of world models, enabling the robot to identify its morphology, all within the framework of a cognitive architecture. Experimental results showcase the effectiveness of this approach in both real and simulated environments., This work was funded by the European Union’s Horizon 2020, research and innovation programme under GA 101070381 (‘PILLAR-Robots’), by MCIN (PID2021-126220OB-I00), by Xunta de Galicia (EDC431C-2021/39), and by the Xunta de Galicia (ED481B). Special thanks to the CESGA., Xunta de Galicia; EDC431C-2021/39, Xunta de Galicia; ED481B
RUC. Repositorio da Universidade da Coruña
Publication Contribución de congreso (ConferenceOutput)

Towards Efficient Knowledge Reuse for Open-ended Learning in Real Robots through Motivation

  • Romero, Alejandro
  • Bellas, Francisco
  • Becerra Permuy, José Antonio
  • Duro, Richard J.
Manuscrito aceptado, [Abstract] The current work is focused on providing robotic systems with mechanisms that support lifelong open-ended learning, with the aim of increasing their real autonomy level. In this general scope, robots must discover their goals and learn the skills to achieve them in a priori unknown domains and tasks. Moreover, they must do it in way that allows this knowledge to be reused later to face new situations properly. To advance in this challenging field, this paper describes a specific motivation-based knowledge reuse strategy, together with the contextual processing carried out, within the e-MDB cognitive architecture. This strategy supports the reuse and adaptation of knowledge acquired in previously seen domains to new ones. It has been validated in a real-world experiment with the Baxter robot, which is analyzed and discussed here, that addresses open-ended interaction in a sequence of domains related to object manipulation., This work was partially funded by MCIN/AEI/10.13039/501100011033 (grant PID2021-126220OB-I00) and by “ERDF A way of making Europe”, Xunta de Galicia (grant EDC431C-2021/39), Centro de Investigación de Galicia “CITIC” (grant ED431G 2019/01), and by Horizon Europe, GA 101070381 “PILLAR-Robots - Purposeful Intrinsically-motivated Lifelong Learning Autonomous Robots'”., Xunta de Galicia; EDC431C-2021/39, Xunta de Galicia; ED431G 2019/01