Skip to main content

EXPLICABILIDAD EN LA TOMA DE DECISIONES DE ROBOTS AUTONOMOS (EDMAR)

PID2021-126592OB-C21

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprogram Subprograma Estatal de Generación de Conocimiento
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2021
State Plan 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSIDAD DE LEÓN

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

Analyzing the influence of the sampling rate in the detection of malicious traffic on flow data

  • Campazas Vega, Adrián
  • Crespo Martínez, Ignacio Samuel
  • Guerrero Higueras, Ángel Manuel
  • Álvarez Aparicio, Claudia
  • Matellán Olivera, Vicente
  • Fernández Llamas, Camino
[EN] Cyberattacks are a growing concern for companies and public administrations. The literature shows that analyzing network-layer traffic can detect intrusion attempts. However, such detection usually implies studying every datagram in a computer network. Therefore, routers routing a significant volume of network traffic do not perform an in-depth analysis of every packet. Instead, they analyze traffic patterns based on network flows. However, even gathering and analyzing flow data has a high-computational cost, and therefore routers usually apply a sampling rate to generate flow data. Adjusting the sampling rate is a tricky problem. If the sampling rate is low, much information is lost and some cyberattacks may be neglected, but if the sampling rate is high, routers cannot deal with it. This paper tries to characterize the influence of this parameter in different detection methods based on machine learning. To do so, we trained and tested malicious-traffic detection models using synthetic flow data gathered with several sampling rates. Then, we double-check the above models with flow data from the public BoT-IoT dataset and with actual flow data collected on RedCAYLE, the Castilla y León regional academic network., SI
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

Optimized Network for Detecting Burr-Breakage in Images of Milling Workpieces

  • Riego Del Castillo, Virginia
  • Sánchez González, Lidia
  • Strisciuglio, Nicola
[EN] Quality standards fulfilment is an essential task in manufacturing processes that involves high costs. One target is to avoid the presence of burrs in the edge of machine workpieces, which reduce the quality of the products. Furthermore, they are not easily removed since the part can even be damaged. In this paper, we propose an optimized Convolutional Neural Network, to detect the presence of burrs in images of milling parts. Its design is focused on the optimization of classification (accuracy) and performance metrics (training time and number of trainable parameters). The proposed architecture identifies burrs with a 91.16\% accuracy in the test set, outperforming existing models as EfficientNetB0. It also reduces the number of trainable parameters from other models as AlexNet by 1.5 million. The prediction process just takes 48.39 milliseconds per image. Finally, in order to check if the model gets a high activation in the region of interest, a visual explanation of the model is also carried out by using Gradient-weighted Class Activation Mapping., SI
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

A robot-based surveillance system for recognising distress hand signal

  • Riego Del Castillo, Virginia
  • Sánchez González, Lidia
  • González Santamarta, Miguel Ángel
  • Rodríguez Lera, Francisco Javier
[EN] Unfortunately, there are still cases of domestic violence or situations where it is necessary to call for help without arousing the suspicion of the aggressor. In these situations, the help signal devised by the Canadian Women's Foundation has proven to be effective in reporting a risky situation. By displaying a sequence of hand signals, it is possible to report that help is needed. This work presents a vision-based system that detects this sequence and implements it in a social robot, so that it can automatically identify unwanted situations and alert the authorities. The gesture recognition pipeline presented in this work is integrated into a cognitive architecture used to generate behaviours in robots. In this way, the robot interacts with humans and is able to detect if a person is calling for help. In that case, the robot will act accordingly without alerting the aggressor. The proposed vision system uses the MediaPipe library to detect people in an image and locate the hands, from which it extracts a set of hand landmarks that identify which gesture is being made. By analysing the sequence of detected gestures, it can identify whether a person is performing the distress hand signal with an accuracy of 96.43%., SI, Agencia Estatal de Investigación, EDMAR Project PID2021-126592OB-C21 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

MERLIN2: MachinEd Ros 2 pLanINg

  • González Santamarta, Miguel Ángel
  • Rodríguez Lera, Francisco Javier
  • Fernández Llamas, Camino
  • Matellán Olivera, Vicente
Permanent link to code/repository used for this code version: https://github.com/SoftwareImpacts/SIMPAC-2023-26, [EN] Any service robot should be able to make decisions and schedule tasks to reach predefined goals such as opening a door or assisting users at home. However, these processes are not single short-term tasks anymore and it is required to set long-term skills for establishing a control architecture that allows robots to perform daily tasks. This paper presents MERLIN2, a hybrid cognitive architecture based on symbolic planning and state machine decision-making systems that allows performing robot behaviors. The architecture can run in any robot running ROS 2, the latest version of the Robot Operative System. MERLIN2 is available at https://github.com/MERLIN2-ARCH/merlin2., SI, Ministerio de Universidades (FPU21/01438), EUROPEAN REGIONAL DEVELOPMENT FUND (ERDF) "Una manera de hacer Europa"
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

A Hybrid Cognitive Architecture to Generate, Control, Plan, and Monitor Behaviors for Interactive Autonomous Robots

  • González Santamarta, Miguel Ángel
  • Rodríguez Lera, Francisco Javier
  • Fernández Llamas, Camino
  • Matellán Olivera, Vicente
Publicación en abierto financiada por el Consorcio de Bibliotecas Universitarias de Castilla y León (BUCLE), con cargo al Programa Operativo 2014ES16RFOP009 FEDER 2014-2020 DE CASTILLA Y LEÓN, Actuación:20007-CL - Apoyo Consorcio BUCLE, [EN] Interactive robots not only need to react in predefined or deterministic scenarios but also learn and adapt in real-time, mirroring cognitive flexibility akin to human intelligence. Achieving this autonomy entails developing cognitive architectures that integrate reactive, deliberative and emergent capabilities. Thus, this paper presents MERLIN2, a hybrid cognitive architecture to generate, control, plan, and monitor behaviors in autonomous robots. This architecture combines reactive, deliberative, and emergent components, aiming to enhance adaptability in dynamic environments and make intelligent real-time decisions, thereby improving autonomy and performance. MERLIN2 comprises a deliberative system, based on a knowledge base and a symbolic planner; and a behavioral system composed of reactive components and several emergent components. It addresses core cognitive aspects like action selection, perception, memory, learning, reasoning, and explainability. MERLIN2 is evaluated in a simulated world and in the real world Carry My Luggage task from the RoboCup@Home. Therefore, the experimentation presented in this article showcases the architecture as a valid solution for autonomous robots., SI
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

SAILOR: perceptual anchoring for robotic cognitive architectures

  • González Santamaría, Miguel Á.
  • Rodríguez Lera, Francisco Javier
  • Matellán Olivera, Vicente
  • Riego Del Castillo, Virginia
  • Sánchez González, Lidia
[EN] Symbolic anchoring is an important topic in robotics, as it enables robots to obtain symbolic knowledge from the perceptual information acquired through their sensors and maintain the link between that knowledge and the sensory data. In cognitive-based robots, this process of transforming sub-symbolic data generated by sensors to obtain and maintain symbolic knowledge is still an open problem. To address this issue, this paper presents SAILOR, a framework for symbolic anchoring integrated into ROS 2. SAILOR aims to maintain the link between symbolic data and perceptual data in real robots over time. It provides a semantic world modeling approach using two deep learning-based sub-symbolic robotic skills: object recognition and matching function. The object recognition skill allows the robot to recognize and identify objects in its environment, while the matching function enables the robot to decide if new perceptual data corresponds to existing symbolic data. This paper describes the proposed method and the development of the framework, as well as its integration in MERLIN2 (a hybrid cognitive architecture fully functional in robots running ROS 2) and the validation of SAILOR using public datasets and a real-world scenario., [ES] El anclaje simbólico es un tema importante en robótica, ya que permite a los obtener conocimientos simbólicos a partir de la información perceptiva perceptiva y mantener el vínculo entre ese conocimiento y los datos sensoriales. conocimiento y los datos sensoriales. En los robots cognitivos, este proceso de transformar los datos subsimbólicos generados por los sensores para obtener y obtener y mantener el conocimiento simbólico. Para abordar esta Este artículo presenta SAILOR, un marco para el anclaje simbólico integrado en ROS2. integrado en ROS 2. SAILOR pretende mantener el vínculo entre los datos simbólicos simbólicos y los datos perceptivos en robots reales a lo largo del tiempo. Proporciona un enfoque de modelado semántico del mundo mediante dos habilidades robóticas dos habilidades robóticas subsimbólicas basadas en el aprendizaje profundo: el reconocimiento de objetos y la función de emparejamiento. La habilidad de reconocimiento de objetos permite al robot reconocer e identificar objetos en su entorno, mientras que la función de coincidencia permite al permite al robot decidir si los nuevos datos perceptivos se corresponden con los datos simbólicos existentes. simbólicos existentes. En este artículo se describe el método propuesto y el desarrollo de del marco, así como su integración en MERLIN2 (una arquitectura cognitiva híbrida híbrida totalmente funcional en robots que ejecutan ROS 2) y la validación de SAILOR mediante conjuntos de datos públicos y un escenario real. (Traducido del abstract original), SI, Agencia Estatal de Investigación, Instituto Nacional de Ciberseguridad, This work has been partially funded by an FPU fellowship provided by the Spanish Ministry of Universities (FPU21/01438), the Grant PID2021-126592OB-C21 funded by MCIN/AEI/10.13039/501100011033 and by ERDF A way of making Europe, and the Grant TED2021-132356B-I00 funded by MCIN/ AEI/10.13039/501100011033 and by the “European Union NextGenerationEU/PRTR”. This research is part of the project TESCAC, financed by “European Union NextGeneration-EU, the Recovery Plan, Transformation and Resilience, through INCIBE
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

Accountability as a service for robotics: Performance assessment of different accountability strategies for autonomous robots

  • Fernández Becerra, Laura
  • Guerrero Higueras, Ángel Manuel
  • Rodríguez Lera, Francisco Javier
  • Matellán Olivera, Vicente
[EN] An essential requirement for increasing human confidence in computer systems is knowing an event’s origin. Therefore, it is necessary to have an efficient method to record such information. It is especially challenging in robotics, where unexpected behaviours can have unpredictable consequences, endangering the interests of people or even their safety. Furthermore, to analyse an incident’s cause or anticipate future behaviours, we must identify the events that cause a specific action. Although it is common to use logging systems for such purposes, issues such as partial recording of events, unhelpful data or the impact on robot performance suggest conceiving new accountability solutions that assist when determining the responsible entities or the provenance of specific information. This paper presents a general-purpose approach to developing an accountability system for autonomous robots. It consists of four main components: a system event logger, a message producer, a distributed event streaming platform and a database. Our proposal is completely decoupled from the monitored system and allows real-time analysis, improving flexibility, besides system protection and transparency. Finally, the need to reduce the impact of the audit process and logging tasks on robot performance has promoted the development of different assessment scenarios to determine the best strategy for providing accounting services., SI, This research has been partially supported under the Grant PID2021-126592OB-C21 funded by MCIN/AEI/ 10.13039/501100011033 and by “ERDF A way of making Europe”; under the grant TED2021-132356B-I00 funded by MCIN/AEI/10.13039/501100011033 and by the “European Union NextGenerationEU/PRTR”; and by the Recovery, Transformation, and Resilience Plan, financed by the European Union (Next Generation) thanks to the TESCAC project (Traceability and Explainability in Autonomous Systems for improved Cybersecurity) granted by INCIBE to the University of León.
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

Cognitive Architectures in Autonomous Robotics: A Systematic Review of Behavior Generation Approaches and Evaluation Strategies

  • González Santamarta, Miguel Ángel
  • Rodríguez Lera, Francisco Javier
  • Matellán Olivera, Vicente
[EN] Cognitive architectures are an essential component in the development of intelligent autonomous robots, enabling planning, learning, and adaptation to dynamic environments. This paper presents a systematic review of the literature focused on cognitive architectures applied to behavior generation in autonomous robotics. A structured search and selection process was conducted using multiple scientific databases, applying explicit inclusion, exclusion, and quality assessment criteria. From an initial set of 502 studies, 22 publications (2018–mid-2025) were selected for in-depth analysis. The review identifies a growing trend toward hybrid architectures that integrate symbolic reasoning with data-driven methods, such as neural networks and behavior trees. The types of architectures, tools used (such as symbolic planners, neural networks, and behavior trees), middleware employed (with a predominance of Robot Operating System), as well as the methods and metrics used in their evaluation, are analyzed. This review provides a detailed overview of the state of the art and highlights the technologies and approaches currently most widely used in the design of cognitive robotic systems., SI, This work was supported in part by the European Union (EU) through the Horizon Europe Project funded by Ministerio de Ciencia, Innovación y Universidades (MICIU)/Agencia Estatal de Investigación (AEI)/10.13039/501100011033 and ‘‘European Regional Development Fund (ERDF)/EU’’ under Grant 101070254 CORESENSE, Grant EDMAR PID2021-126592OB-C21, and Grant AURORAS PID2024-161761OB-C21
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

A Roadmap for Responsible Robotics: Promoting Human Agency and Collaborative Efforts

  • Araiza Illan, Dejanira
  • Baum, Kevin
  • Chatila, Raja
  • Moth-Lund Christensen, Sarah
  • Coghlan, Simon
  • Collins, Emily
  • Conroy, S. Kate
  • Cunha, Alcino
  • Dobrosovestnova, Anna
  • Duijf, Hein
  • Evers, Vanessa
  • Fisher, Michael
  • Hochgeschwender, Nico
  • Kökciyan, Nadin
  • Lemaignan, Séverin
  • Rodríguez Lera, Francisco Javier
  • Ljungblad, Sara
  • Magnusson, Martin
  • Mansouri, Masoumeh
  • Milford, Michael
  • Moon, A. Jung
  • Powers, Thomas M.
  • Salvini, Pericle
  • Scantamburlo, Teresa
  • Schuster, Nick
  • Slavkovik, Marija
  • Topcu, Ufuk
  • Vanegas, Daniel
  • Wasowski, Andrzej
  • Yang, Yi
[EN] This document presents the outcomes of the Dagstuhl Seminar “Roadmap for Responsible Robotics,” held in September 2023 at the Leibniz Center for Informatics, Schloss Dagstuhl, Germany. The seminar brought together researchers from the fields of robotics, computer science, social and cognitive sciences, and philosophy with the aim of charting a path toward improving responsibility in robotic systems. Through intensive interdisciplinary discussions centered on the various values at stake as robotics increasingly integrates into human life, the participants identified key priorities to guide future research and regulatory efforts. The resulting road map outlines actionable steps to ensure that robotic systems coevolve with human societies, promoting human agency and humane values rather than undermining them. Designed for diverse stakeholders—researchers, policy makers, industry leaders, practitioners, nongovernmental organizations (NGOs), and civil society groups—this road map provides a foundation for collaborative efforts toward responsible robotics., SI, This work was made possible through the Dagstuhl Seminar on “Roadmap for Responsible Robotics” (23371). In addition, we acknowledge the following sources of support for individual authors. Fisher is supported by the U.K. Royal Academy of Engineering’s Chair in Emerging Technologies scheme, and the work is partially funded by the Engineering and Physical Sciences Research Council in the United Kingdom, through t he Computationa l Agent Responsibility project (EP/W01081X/1). Rodríguez-Lera is supported by Grant P I D 2 0 21-1 2 6 5 9 2 O B - C 21 f u n d e d b y M I C I U / AEI/10.13039/501100011033 and by the EU’s European Regional Development Fund (ERDF). Ljungblad is supported by Wallenberg AI, Autonomous Systems and Software Pro- gram, Humanity and Society. Moon is supported by the Natu- ral Sciences and Engineering Research Council of Canada. Baum is supported by the German Research Foundation under Grant 389792660 as part of TRR 248 (see https://perspicuous- computing.science), by the German Federal Ministry of Edu- cation and Research as part of the project MAC-MERLin (Grant Agreement 01IW24007), and by the ERDF and the Saarland within the scope of (To)CERTAIN. Salvini is sup- ported by the EPSRC research project RoboTIPS: Developing Responsible Robots for the Digital Economy (EP/S005099/1).
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

A systematic literature review of unsupervised learning algorithms for anomalous traffic detection based on flows

  • Miguel Diez, Alberto
  • Campazas Vega, Adrián
  • Álvarez Aparicio, Claudia
  • Esteban Costales, Gonzalo
  • Guerrero Higueras, Ángel Manuel
[EN] The constant increase of devices connected to the Internet, and therefore of cyber-attacks, makes it necessary to analyse network traffic in order to recognize malicious activity. Traditional packet-based analysis methods are insufficient because in large networks the amount of traffic is so high that it is unfeasible to review all communications. For this reason, network flows is a suitable approach for this situation, which in future 5G networks will have to be used, as the number of packets will increase dramatically. If this is also combined with unsupervised learning models, it can detect new threats for which it has not been trained. This paper presents a systematic review of the literature on unsupervised learning algorithms for detecting anomalies in network flows, following the PRISMA guideline. A total of 63 scientific articles have been reviewed, analysing 15 of them in depth. The results obtained show that autoencoder is the most used option, followed by SVM, ALAD, or SOM. On the other hand, all the datasets used for anomaly detection have been collected, including some specialised in IoT or with real data collected from honeypots., SI
BULERIA. Repositorio Institucional de la Universidad de León
Publication Artículo científico (JournalArticle)

Robocup 2023-2024 ROSbag Dataset

  • González Fernández, Irene
  • Peña Narváez, Juan Diego
  • Guerrero Hernandéz, José Miguel
  • Pérez Rodríguez, Rodrigo
  • González Cantón, Alejandro
  • Rodríguez Lera, Francisco Javier
[EN] This dataset was collected during the 2023 and 2024 RoboCup competitions using the TIAGo robot equipped with an RGB-D camera, a Hokuyo laser, and a RODE microphone. The dataset includes ROSbag files that capture the robot's sensory data and planning task behavior, as well as video recordings that provide third-person perspectives of task execution. These data provide information about the performance of autonomous robots in social tasks and navigation in dynamic environments with human interaction., SI, The CORESENSE project is funded by the EC Horizon Europe program through grant HE #101070254 inside the HORIZON-CL4-2021-DIGITAL-EMERGING-01-11 topic.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Defining a Standard Blockchain-based Black Box for Autonomous Systems

  • Inyesto-Alonso, Laura
  • Sobrín-Hidalgo, David
  • Álvarez-Aparicio, Claudia
  • Campazas-Vega, Adrián
  • Guerrero-Higueras, Ángel M.
  • Matellán Olivera, Vicente
Human-system interaction demands a high level of security, especially for those systems that work autonomously. In environments where humans and autonomous systems coexist, safety is crucial because an autonomous system malfunction can put the human’s physical integrity at risk. In the same way that an airplane integrates a black box system to record the relevant data during the flight, autonomous machines should integrate their own black box system. Implementing a black box in autonomous systems would help to determine the cause of incidents and assign responsibility after an unexpected event occurs. However, there is currently no consensus on a standard for building black boxes for autonomous physical systems. For this reason, this paper proposes a standard for defining the information that should be recorded by an autonomous system black box. The proposed approach combines this standard with blockchain technology, providing security and tamper-resistance to ensure the integrity of the black box data.