Pasar al contenido principal

EXPLICACION Y APRENDIZAJE DESDE LA AUTO-EXTENSION

PID2022-137344OB-C32

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE MALAGA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

CORTEX as an Enabler of Multi-platform Integration in Internet of Robotics Things ecosystems

  • Tudela, Alberto
  • Galeas, José
  • Pons, Óscar
  • Madrid, Carlos
  • Aguilera, Sara
  • Gómez, Pablo
  • Bandera, Juan Pedro
  • Bandera, Antonio
  • Bustos, Pablo
The integration of robotic technology in an Internet of Things (IoT) environment is known as the Internet of Robotics Things (IoRT). The benefits that this integration can bring have been highlighted in recent publications. One of the application scenarios is the Ambient Assistant Living (AAL) environment. The environment is equipped with appropriate sensors to provide the robot with more detailed knowledge of the context, while the robot can move around the environment and interact with the people in it, capturing knowledge that can help to improve the AAL’s behaviour. This paper describes the deployment of an IoRT ecosystem within a small apartment based on the CORTEX software architecture. The use of CORTEX has allowed us to integrate different frameworks (wireless network, micro-ROS, ROS 2, RoboComp, Mira) into this ecosystem relatively easily, connecting them all to the same knowledge representation. In addition to other use cases, the main goal of this deployment is to be able to monitor both the position and certain vital parameters of an elderly person living alone at home.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Enhanced Robot Navigation in a Cyber-Physical System-of-Systems Architecture

  • Tudela, Alberto
  • Galeas, José
  • Pons, Óscar
  • Bandera, Juan Pedro
  • Bandera, Antonio
The idea of introducing a robot into an Ambient Assisted Living (AAL) environment to provide additional services to those provided by the environment itself has been exploited in numerous projects. Moreover, new opportunities can arise from this symbiosis, which usually require both systems to share the knowledge (and not just the data) they capture from the context. Thus, using knowledge elaborated from the raw data captured by the sensors deployed in the environment, the robot can know where the person is, whether he/she should do some physical exercise, but also whether he/she should move a chair away to allow the robot to successfully complete a task. This paper describes how to extend the CORTEX software architecture to handle and merge, partially and task-specifically, the state representations built by the robot and the AAL system. In particular, we show how this symbiotic framework allows the robot to trace routes on a semantically annotated metric map updated with information obtained from sensors located in an AAL environment.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

On the use of ontologies as knowledge source for social robots the INSIGHT research project

  • Martínez-Gómez, Jesús
  • García-Varea, Ismael
  • Flores, M. Julia
  • Ossa, Luis de la
  • Ballesteros-Jerez, Javier
  • Bandera, Antonio
  • Marfil Robles, Rebeca
  • Bachiller Burgos, Pilar
  • Bustos, Pablo
As in many other disciplines, social robotics has been influenced by the advent of new trends in massive data acquisition and processing. While there are several areas where algorithms directly trained from data are exceedingly useful, such as object detection or speech recognition, the core reasoning of a robot still requires knowledge provided by human supervisors, rather than being directly derived from data. In this work, we analyse the role of ontologies and causal reasoning for this purpose, and we review the necessary steps to adapt existing ontologies to a specific use case within the INSIGHT research project.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Upgrading the cognitive architecture of a robot to become socially aware

  • Galeas, José
  • Núñez, Pedro
  • Tudela, Alberto
  • Jerez, Antonio
  • Pons, Óscar
  • Bandera, Juan Pedro
Socially Assistive Robots are becoming an important technology to cope with the deep demographic changes of the coming society. These robots are a versatile tool for caregivers and can add value to the services provided in care centers such as retirement homes. However, to meet these expectations, they need to address important challenges. They need to be not only functional, but also acceptable, useful and accessible. They need to adapt their behaviour not only to the physical but also to the social context, adapting their behaviour to the preferences, expectations and needs of the people around them. They also need to explain their behaviour, going beyond data-driven explanations to include causal reasoning. This paper presents the research work carried out in the CAMPERO and SHADOW national projects to implement a socially assistive robot capable of adapting to the social context. This work has been dedicated to the improvement of previous robotic platforms, and also to produce a shared cognitive architecture that includes adaptation mechanisms, different types of memory, and deep multi-agent synchronization. The paper describes the results of functional tests that have been carried out in laboratory environments, before the robot is deployed in a retirement home for a long-term evaluation of the user experience.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Integration of a Sign Language Interface in a Socially Assistive Robot

  • Bouhou, Sohaila Chtioui
  • Tudela, Alberto
  • Galeas, José
  • Pons, Óscar
  • Bandera, Antonio
  • Romero-Garcés, Adrián
This work aims to design and implement a Sign Language interface to improve the communication of deaf people in hospital and telemedical environments. Using Mediapipe to detect landmarks and a Random Forest classifier to interpret gestures, a system capable of recognising and translating signs in real time has been developed. The interface includes an intuitive graphical application developed in Tkinter that allows the visualisation of the recognised signs and facilitates interaction with the user. In addition, detection modes for both letters and numbers have been implemented, and mechanisms for remote communication and system updating have been considered. The interface was integrated into a prototype robot to test its functionality in real environments.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Graph-based inner state prediction for a socially aware robot

  • Tejón-Moreno, José
  • Bandera, Juan Pedro
  • Bandera, Antonio
  • Romero-Garcés, Adrián
Robots working and interacting with people in daily life scenarios require to be aware of their context, both physical and social. Predictive capabilities allow the robot to adapt to its context, and are a key component of awareness. This paper presents a system that uses the current and past context knowledge to infer future context. This system is integrated into CORTEX, a cognitive architecture where immediate context is represented as an oriented graph, the Deep State Representation. The proposed approach is based on collecting and classifying all the information obtained from the executions of use cases performed in the past by the robot. Then it uses these data to train a Graph Neural Network to predict the next configuration of the Deep State Representation. The used neural network is a graph convolutional network. This kind of network uses the information of adjacent nodes in order to make predictions in the graph. The results presented in this paper shows that the proposed system is able to predict next states with a precision close to 100% for a known use case, using manually generated data for training, validation and test.