Examinando por Autor "Vazquez, Juan-Ignacio"
Mostrando 1 - 8 de 8
Resultados por página
Opciones de ordenación
Ítem Adaptive robot behavior based on human comfort using reinforcement learning(Institute of Electrical and Electronics Engineers Inc., 2024) González Santocildes, Asier; Vazquez, Juan-Ignacio ; Eguíluz, AndoniThis study explores the potential of training robots using reinforcement learning (RL) to adapt their behavior based on human comfort levels during tasks. An experimental environment has been developed and made available to the research community, facilitating the replication of these experiments. The results demonstrate that adjusting a single comfort-related input parameter during training leads to significant variations in the robot's behavior. Detailed discussions of the reward functions and obtained results validate these behavioral adaptations, confirming that robots can dynamically respond to human needs, thereby enhancing human-robot interaction. While the study highlights the effectiveness of this approach, it also raises the question of real-time comfort measurement, suggesting various systems for future exploration. These findings contribute to the development of more intuitive and emotionally responsive robots, offering new possibilities for future research in advancing human-robot interaction.Ítem Architecture for WSN nodes integration in context aware systems using semantic messages(Springer, 2010) Larizgoitia, Iker; Muguira Urtubi, Leire; Vazquez, Juan-IgnacioWireless sensor networks (WSN) are becoming extremely popular in the development of context aware systems. TraditionallyWSN have been focused on capturing data, which was later analyzed and interpreted in a server with more computational power. In this kind of scenario the problem of representing the sensor information needs to be addressed. Every node in the network might have different sensors attached; therefore their correspondent packet structures will be different. The server has to be aware of the meaning of every single structure and data in order to be able to interpret them.Multiple sensors, multiple nodes, multiple packet structures (and not following a standard format) is neither scalable nor interoperable. Context aware systems have solved this problem with the use of semantic technologies. They provide a common framework to achieve a standard definition of any domain. Nevertheless, these representations are computationally expensive, so a WSN cannot afford them. The work presented in this paper tries to bridge the gap between the sensor information and its semantic representation, by defining a simple architecture that enables the definition of this information natively in a semantic way, achieving the integration of the semantic information in the network packets. This will have several benefits, the most important being the possibility of promoting every WSN node to a real semantic information source. © 2010 ICST Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering.Ítem Enhancing robot behavior with EEG, reinforcement learning and beyond: a review of techniques in collaborative robotics(Multidisciplinary Digital Publishing Institute (MDPI), 2024-07-20) González Santocildes, Asier; Vazquez, Juan-Ignacio; Eguíluz, AndoniCollaborative robotics is a major topic in current robotics research, posing new challenges, especially in human–robot interaction. The main aspect in this area of research focuses on understanding the behavior of robots when engaging with humans, where reinforcement learning is a key discipline that allows us to explore sophisticated emerging reactions. This review aims to delve into the relevance of different sensors and techniques, with special attention to EEG (electroencephalography data on brain activity) and its influence on the behavior of robots interacting with humans. In addition, mechanisms available to mitigate potential risks during the experimentation process such as virtual reality are also be addressed. In the final part of the paper, future lines of research combining the areas of collaborative robotics, reinforcement learning, virtual reality, and human factors are explored, as this last aspect is vital to ensuring safe and effective human–robot interactions.Ítem An environment adaptive ZigBee-based indoor positioning algorithm(IEEE, 2010) Larranaga, Janire; Muguira Urtubi, Leire; López Garde, Juan Manuel; Vazquez, Juan-IgnacioLately, there has been significant progress in the field of wireless communications and networking. Furthermore, the number of applications that require context information as the user's location will increase in the coming years. However, this issue still has not been solved indoors due to the RF (Radio Frequency) signals' behaviour in this kind of scenarios. In this paper, we present a robust, easy to deploy and flexible indoor localization system based on ZigBee Wireless Sensor Networks. It is important to mention that our localization system is based on RSSI (Received Signal Strength Indicator) level measurements since this information can be obtained directly from the messages exchanged between nodes, so no extra hardware is required. Our localization system consists of two phases: calibration and localization. Anytime a blind node needs to be located, our system performs calibration using a matrices system, so that the environment can be characterized, taking into account possible changes on it since the last request. Then, in the localization phase, the central server processes all the information and calculates the blind node's position with the new iterative algorithm we present. With this indoor positioning algorithm we can estimate the blind node's position with a good resolution (3 m average error), so we can say that this ZigBee localization algorithm provides very promising results.Ítem Gesture-based human machine interaction using RCNNs in limited computation power devices(NLM (Medline), 2021-12-08) Tellaeche Iglesias, Alberto ; Fidalgo Astorquia, Ignacio ; Vazquez, Juan-Ignacio ; Saikia, SurajitThe use of gestures is one of the main forms of human machine interaction (HMI) in many fields, from advanced robotics industrial setups, to multimedia devices at home. Almost every gesture detection system uses computer vision as the fundamental technology, with the already well-known problems of image processing: changes in lighting conditions, partial occlusions, variations in color, among others. To solve all these potential issues, deep learning techniques have been proven to be very effective. This research proposes a hand gesture recognition system based on convolutional neural networks and color images that is robust against environmental variations, has a real time performance in embedded systems, and solves the principal problems presented in the previous paragraph. A new CNN network has been specifically designed with a small architecture in terms of number of layers and total number of neurons to be used in computationally limited devices. The obtained results achieve a percentage of success of 96.92% on average, a better score than those obtained by previous algorithms discussed in the state of the art.Ítem Interacting with the digital world through RFID-powered gadgets(IEEE, 2009) Muguira Urtubi, Leire; Ruiz de Garibay Pascual, Jonathan; Vazquez, Juan-IgnacioThe Internet of Things is a field of the Future Internet that has a significant support from different institutions. Research has been done in this area for years and although it has progressed significantly, their goals remain the same: designing innovative Internet-connected experiences and augmenting existing objects' capabilities with Internet-related features. The scientific community has explored new ways and concepts, such as, service generation and consumption or user interaction. In this paper we present our work on creating RFID-based smart gadgets in order to take Internet experience to the next level, merging the on-line and the tangible worlds into a single continuous space.Ítem Internet browsing through RFID-powered gadgets(IOS Press, 2009) Muguira Urtubi, Leire; Ruiz de Garibay Pascual, Jonathan; Vazquez, Juan-IgnacioThe vision of the Internet of Things is challenging researchers from different fields with the common goal of designing innovative Internet-connected experiences or augmenting existing objects' capabilities with Internet-related features. During these first stages, researchers must explore new ways and concepts, and share the results with the scientific community. In this paper, we present our work on creating RFID-based smart gadgets in order to take Internet experience to the next level, merging the on-line and the tangible worlds into a single continuous space.Ítem RFIDGlove: a wearable RFID reader(IEEE, 2009) Muguira Urtubi, Leire; Vazquez, Juan-Ignacio; Arruti, Asier; Ruiz de Garibay Pascual, Jonathan; Mendia, Izaskun; Renteria, SilviaThere are different experiences in the use of RFID technology for warehouse inventories. However, there is future work to do on the design of advanced reading devices, applying wearable computation techniques and wireless communications. The aim of this work is to allow a natural interaction for the user who performs inventory tasks. In this paper we show the RFIDGlove system, which consists of a glove with an integrated RFID reader, an organic micro display and a communication system. The RFIDGlove system increases the efficiency of the activities in these areas, improving the user's experience and comfort while he/she uses the system. © 2009 IEEE.