Pablo Bustos | Universidad de Extremadura (original) (raw)

Papers by Pablo Bustos

Lecture notes in networks and systems, Nov 19, 2022

Lecture Notes in Computer Science, 2016

Collaboration is an essential feature of human social interaction. Briefly, when two or more peop... more Collaboration is an essential feature of human social interaction. Briefly, when two or more people agree on a common goal and a joint intention to reach that goal, they have to coordinate their actions to engage in joint actions, planning their courses of actions according to the actions of the other partners. The same holds for teams where the partners are people and robots, resulting on a collection of technical questions difficult to answer. Human-robot collaboration requires the robot to coordinate its behavior to the behaviors of the humans at different levels, e.g., the semantic level, the level of the content and behavior selection in the interaction, and low-level aspects such as the temporal dynamics of the interaction. This forces the robot to internalize information about the motions, actions and intentions of the rest of partners, and about the state of the environment. Furthermore, collaborative robots should select their actions taking into account additional human-aware factors such as safety, reliability and comfort. Current cognitive systems are usually limited in this respect as they lack the rich dynamic representations and the flexible human-aware planning capabilities needed to succeed in tomorrow human-robot collaboration tasks. Within this paper, we provide a tool for addressing this problem by using the notion of deep hybrid representations and the facilities that this common state representation offers for the tight coupling of planners on different layers of abstraction. Deep hybrid representations encode the robot and environment state, but also a robot-centric perspective of the partners taking part in the joint activity.

This paper describes the genesis of Gualzru, a robot commissioned by a large Spanish technologica... more This paper describes the genesis of Gualzru, a robot commissioned by a large Spanish technological company to provide advertisement services in open public spaces. Gualzru has to stand by at an interactive panel observing the people passing by and, at some point, select a promising candidate and approach her to initiate a conversation. After a small verbal interaction, the robot is supposed to convince the passerby to walk back to the panel, leaving the rest of the selling task to an interactive software embedded in it. The whole design and building process took less than three years of team composed of five groups at different geographical locations. We describe here the lessons learned during this period of time, from different points of view including the hardware, software, architectural decisions and team collaboration issues.

Robotics and Autonomous Systems, 2021

Journal of Physical Agents (JoPha), 2017

EURASIP Journal on Image and Video Processing, 2017

Upon publication of the original article [1], it was noticed that in the caption of Fig. 2, there... more Upon publication of the original article [1], it was noticed that in the caption of Fig. 2, there is a typographical error in the expression " p ≥ ∫p i " that defines the cell positions for which a point ei should vote. The correct expression is " p > =pi " This has now been acknowledged and corrected in this erratum. The original article has been corrected.

Biosystems & Biorobotics, 2016

Autonomous robots that are interfaced with virtual or augmented reality gaming are increasingly b... more Autonomous robots that are interfaced with virtual or augmented reality gaming are increasingly being developed to provide repetitive intensive practice to promote increased compliance and facilitate better outcomes in neurorehabilitation therapies. These therapist robots, equipped with a set of sensors and actuators for monitorizing the environment, allows health professionals to supervise the recovery of patients with serious disability. In this paper, a new system for supervising neuro-rehabilitation therapies using autonomous robots is presented. The therapy explained in this work is based on a set of virtual reality games developed by using robotics technologies, such as RGB-D camera and depth image processing. Three different virtual reality games have been developed in the application to gain better outcomes during the therapy, each one focuses on a typical exercise: ‘Touch the apple’, ‘Follow the path’ and ‘Imitate the dance’. Both, the virtual reality games and the main robotics technologies for their development, are explained in this paper.

espanolLa gran cantidad de datos recopilados por los sensores inteligentes representan un recurso... more espanolLa gran cantidad de datos recopilados por los sensores inteligentes representan un recurso de gran valor que se puede utilizar para entender mejor el comportamiento de los usuarios y asi poder optimizar el consumo y las necesidades de los edificios publicos. Existe actualmente un interes creciente en la comunidad internacional para hacer uso del historico de datos con el objetivo de predecir el consumo de energia o de agua, por ejemplo, de forma que la demanda pueda ser adaptada de forma dinamica e incluso pueda generarse alertas en caso de diferencias bruscas entre el consumo estimado y los datos reales adquiridos por los sensores. El presente articulo detalla el analisis de datos relativos al consumo de agua en la Escuela Politecnica de la Universidad de Extremadura dentro del Proyecto de centro SmartPoliTech. Este proyecto es una iniciativa creada en dicho centro cuyo objetivo es transformar las instalaciones existentes en un espacio experimental para el estudio, analisis, diseno, implantacion y validacion de las tecnologias Smart. Las caracteristicas de esta Escuela como centro universitario publico la convierten en un escenario ideal para investigar en estos nuevos ecosistemas sociales digitales. En particular, este trabajo presenta un sistema predictivo del consumo de agua de la Escuela Politecnica, donde en el mismo se realiza el analisis de los meses mas significativos del historico de datos del centro, extrayendo patrones de consumo tipicos en diferentes meses del ano. En el enfoque propuesto, y una vez los datos son adquiridos a partir de medidores de consumo instantaneos inteligentes, se utiliza el algoritmo Expectation Maximization para realizar un modelo de mezcla de gaussianas sobre los datos, cuyos resultados son presentados en este documento. Los parametros de este modelo de mezcla varian segun el tipo de dia (dia de la semana, fin de semana), y tambien el mes concreto. La metodologia propuesta se aplica a un conjunto de datos reales del historico de datos de los edificios de la Escuela Politenica, y los modelos son validados a continuacion con datos reales durante los ultimos seis meses. Los resultados se cruzan con variables contextuales disponibles como, por ejemplo, dias festivos o periodo de examenes, arrojando resultados interesantes a la hora de estudiar la demanda real en dichas situaciones. EnglishThe large amount of data collected by smart sensors is a resource of great value that can be used to better understand user behavior and thus be able to optimize the consumption and the resource needs of public buildings. There is currently a growing interest in the international community to make use of the historical data in order to predict the consumption of energy or water, for example, so that the demand can be adapted dynamically and even generate alerts in case of sharp differences between the estimated consumption and the real data acquired by the sensors. This article details the analysis of data related to water consumption in the Escuela Politecnica of the University of Extremadura within the SmartPoliTech Center Project. This project is an initiative created in this center whose objective is to transform existing facilities into an experimental space for the study, analysis, design, implementation and validation of Smart technologies. The characteristics of this School as a public university center make it an ideal setting to investigate these new digital social ecosystems. In particular, this work presents a predictive system for water consumption at Escuela Politecnica, where the analysis of the most significant months of its data history is carried out, and extracting typical consumption patterns in different months of the year. In the proposed approach, and once the data is acquired from smart instant consumption meters, the Expectation Maximization algorithm is used to perform a Gaussian mixture model on the data, the results of which are presented in this document. The parameters of this mix model vary according to the type of day (day of the week, weekend), and also the specific month. The proposed methodology is applied to a set of real data of the data history of the buildings of the Escuela Politecnica, and the models are validated below with real data during the last six months. The results are crossed with available contextual variables such as, for example, holidays or exam periods, yielding interesting results when studying the real demand in these situations.

Monitorización y evaluación de la habitabilidad, calidad del aire y eficiencia energética de los edificios: experiencias en España, 2020, ISBN 9788412276749, págs. 50-58, 2020

Sustainable Cities and Society, 2020

This paper presents a methodology to improve energy efficiency and hygrothermal comfort condition... more This paper presents a methodology to improve energy efficiency and hygrothermal comfort conditions in public buildings using low-cost ICTs. A change in the daily users`habits is further on suggested. The process develops circularly in four steps: building definition model, monitoring, analysis, and users' participation. The method has been tested in four similar public buildings of traditional construction. Firstly, a building model has been defined (climatology, thermal envelope and maintenance, interior design, systems, and occupancy). Secondly, a lowcost, scalable, and open-source information system has been installed to collect data of energy consumption, temperature, humidity and CO 2 values. The resulting time series were analysed and compared to the energy consumption bills of the previous three years to obtain the real building behaviour. Data gathered by the sensors and suggestions have been made available to users for real-time monitoring. Furthermore, reliable energy indicators to characterize this building typology in services sector have been obtained. Other sub goals include raising awareness among users about the use of public resources, and the initiation of a smart-village strategy using low-cost technologies. The results highlight inefficient consumption patterns and discomfort situation that should encourage users to take action and reorient municipal policies.

Considering the widespread use of mobile robots in different parts of society, it is important to... more Considering the widespread use of mobile robots in different parts of society, it is important to provide them with the capability to behave in a socially acceptable manner. Therefore, a research topic of great importance recently has been the study of Human-Robot Interaction. Autonomous navigation is a fundamental task in Robotics, and several different strategies that produce paths that are either length or time optimized can be found in the literature. However, considering the recent use of mobile robots in a more social context, the use of such classical techniques is restricted. Therefore, in this article we present a social navigation approach considering environments with groups of people. The proposal uses a density function to efficiently represent groups of people, and modify the navigation architecture in order to include the social behaviour of the robot during its motion. This architecture is based on the combined use of the Probabilistic Road Mapping (PRM) and the Rapidly-exploring Random Tree (RRT) path planners and an adaptation of the elastic band algorithm. Experimental evaluation was carried out in different simulated environments, providing insight on the performance of the proposed technique, which surpasses classical techniques with no proxemics awareness in terms of social impact.

Lecture notes in networks and systems, Nov 19, 2022

IOS Press eBooks, Jun 14, 2022

Soon robots will cooperate with humans in everyday tasks. These robots must be endowed with socia... more Soon robots will cooperate with humans in everyday tasks. These robots must be endowed with social skills so that their behavior will be similar to that of people. One of these behaviors is navigation: how the robot plans the route and moves through ubicomp environments. For example, a social behavior during navigation consists of detecting the position of people and evaluating with proxemics those areas where the robot can move and with what velocity. This work presents a new controller for the following ability of a socially aware person. The robot is equipped with RGB-D and laser sensors and navigates through an ubicomp environment that provides the person's position at every moment. The system initially estimates the person's position and its interaction regions at a future instant and then adjusts its path and velocity based on this estimate. Experimental results in simulated environments are included and discussed as initial results to show the performance of this proposal. We include a set of social metrics to validate the proposed results.

Lecture Notes in Computer Science, 2022

Monitorización y evaluación de la habitabilidad, calidad del aire y eficiencia energética de los edificios: experiencias en España, 2020, ISBN 9788412276749, págs. 254-266, 2020

Journal of Physical Agents (JoPha), 2013

During the last six years the RoboComp robotics framework has been steadily growing in the number... more During the last six years the RoboComp robotics framework has been steadily growing in the number of software components, the variety of robots supported and in new solutions to the maintenance of large robotics software repositories. In this paper we present recent advances in the formal definition of the RoboComp component model and a new set of tools based on Domain Specific Languages that have been created to simplify the whole development cycle of the components. Moreover, a new robot simulation tool has been created providing perfect integration with RoboComp and better control over experiments than current existing simulators. Finally, the paper describes a working solution to the important problem of communications middleware independence, which allows users to decide which middleware the components will be compiled with. Our solution has been validated by the integration of Nerve, a novel middleware for critical robotics tasks, in RoboComp.

Journal of Ambient Intelligence and Humanized Computing, Mar 30, 2022

Lecture notes in networks and systems, Nov 19, 2022

Lecture Notes in Computer Science, 2016

Collaboration is an essential feature of human social interaction. Briefly, when two or more peop... more Collaboration is an essential feature of human social interaction. Briefly, when two or more people agree on a common goal and a joint intention to reach that goal, they have to coordinate their actions to engage in joint actions, planning their courses of actions according to the actions of the other partners. The same holds for teams where the partners are people and robots, resulting on a collection of technical questions difficult to answer. Human-robot collaboration requires the robot to coordinate its behavior to the behaviors of the humans at different levels, e.g., the semantic level, the level of the content and behavior selection in the interaction, and low-level aspects such as the temporal dynamics of the interaction. This forces the robot to internalize information about the motions, actions and intentions of the rest of partners, and about the state of the environment. Furthermore, collaborative robots should select their actions taking into account additional human-aware factors such as safety, reliability and comfort. Current cognitive systems are usually limited in this respect as they lack the rich dynamic representations and the flexible human-aware planning capabilities needed to succeed in tomorrow human-robot collaboration tasks. Within this paper, we provide a tool for addressing this problem by using the notion of deep hybrid representations and the facilities that this common state representation offers for the tight coupling of planners on different layers of abstraction. Deep hybrid representations encode the robot and environment state, but also a robot-centric perspective of the partners taking part in the joint activity.

This paper describes the genesis of Gualzru, a robot commissioned by a large Spanish technologica... more This paper describes the genesis of Gualzru, a robot commissioned by a large Spanish technological company to provide advertisement services in open public spaces. Gualzru has to stand by at an interactive panel observing the people passing by and, at some point, select a promising candidate and approach her to initiate a conversation. After a small verbal interaction, the robot is supposed to convince the passerby to walk back to the panel, leaving the rest of the selling task to an interactive software embedded in it. The whole design and building process took less than three years of team composed of five groups at different geographical locations. We describe here the lessons learned during this period of time, from different points of view including the hardware, software, architectural decisions and team collaboration issues.

Robotics and Autonomous Systems, 2021

Journal of Physical Agents (JoPha), 2017

EURASIP Journal on Image and Video Processing, 2017

Upon publication of the original article [1], it was noticed that in the caption of Fig. 2, there... more Upon publication of the original article [1], it was noticed that in the caption of Fig. 2, there is a typographical error in the expression " p ≥ ∫p i " that defines the cell positions for which a point ei should vote. The correct expression is " p > =pi " This has now been acknowledged and corrected in this erratum. The original article has been corrected.

Biosystems & Biorobotics, 2016

Autonomous robots that are interfaced with virtual or augmented reality gaming are increasingly b... more Autonomous robots that are interfaced with virtual or augmented reality gaming are increasingly being developed to provide repetitive intensive practice to promote increased compliance and facilitate better outcomes in neurorehabilitation therapies. These therapist robots, equipped with a set of sensors and actuators for monitorizing the environment, allows health professionals to supervise the recovery of patients with serious disability. In this paper, a new system for supervising neuro-rehabilitation therapies using autonomous robots is presented. The therapy explained in this work is based on a set of virtual reality games developed by using robotics technologies, such as RGB-D camera and depth image processing. Three different virtual reality games have been developed in the application to gain better outcomes during the therapy, each one focuses on a typical exercise: ‘Touch the apple’, ‘Follow the path’ and ‘Imitate the dance’. Both, the virtual reality games and the main robotics technologies for their development, are explained in this paper.

espanolLa gran cantidad de datos recopilados por los sensores inteligentes representan un recurso... more espanolLa gran cantidad de datos recopilados por los sensores inteligentes representan un recurso de gran valor que se puede utilizar para entender mejor el comportamiento de los usuarios y asi poder optimizar el consumo y las necesidades de los edificios publicos. Existe actualmente un interes creciente en la comunidad internacional para hacer uso del historico de datos con el objetivo de predecir el consumo de energia o de agua, por ejemplo, de forma que la demanda pueda ser adaptada de forma dinamica e incluso pueda generarse alertas en caso de diferencias bruscas entre el consumo estimado y los datos reales adquiridos por los sensores. El presente articulo detalla el analisis de datos relativos al consumo de agua en la Escuela Politecnica de la Universidad de Extremadura dentro del Proyecto de centro SmartPoliTech. Este proyecto es una iniciativa creada en dicho centro cuyo objetivo es transformar las instalaciones existentes en un espacio experimental para el estudio, analisis, diseno, implantacion y validacion de las tecnologias Smart. Las caracteristicas de esta Escuela como centro universitario publico la convierten en un escenario ideal para investigar en estos nuevos ecosistemas sociales digitales. En particular, este trabajo presenta un sistema predictivo del consumo de agua de la Escuela Politecnica, donde en el mismo se realiza el analisis de los meses mas significativos del historico de datos del centro, extrayendo patrones de consumo tipicos en diferentes meses del ano. En el enfoque propuesto, y una vez los datos son adquiridos a partir de medidores de consumo instantaneos inteligentes, se utiliza el algoritmo Expectation Maximization para realizar un modelo de mezcla de gaussianas sobre los datos, cuyos resultados son presentados en este documento. Los parametros de este modelo de mezcla varian segun el tipo de dia (dia de la semana, fin de semana), y tambien el mes concreto. La metodologia propuesta se aplica a un conjunto de datos reales del historico de datos de los edificios de la Escuela Politenica, y los modelos son validados a continuacion con datos reales durante los ultimos seis meses. Los resultados se cruzan con variables contextuales disponibles como, por ejemplo, dias festivos o periodo de examenes, arrojando resultados interesantes a la hora de estudiar la demanda real en dichas situaciones. EnglishThe large amount of data collected by smart sensors is a resource of great value that can be used to better understand user behavior and thus be able to optimize the consumption and the resource needs of public buildings. There is currently a growing interest in the international community to make use of the historical data in order to predict the consumption of energy or water, for example, so that the demand can be adapted dynamically and even generate alerts in case of sharp differences between the estimated consumption and the real data acquired by the sensors. This article details the analysis of data related to water consumption in the Escuela Politecnica of the University of Extremadura within the SmartPoliTech Center Project. This project is an initiative created in this center whose objective is to transform existing facilities into an experimental space for the study, analysis, design, implementation and validation of Smart technologies. The characteristics of this School as a public university center make it an ideal setting to investigate these new digital social ecosystems. In particular, this work presents a predictive system for water consumption at Escuela Politecnica, where the analysis of the most significant months of its data history is carried out, and extracting typical consumption patterns in different months of the year. In the proposed approach, and once the data is acquired from smart instant consumption meters, the Expectation Maximization algorithm is used to perform a Gaussian mixture model on the data, the results of which are presented in this document. The parameters of this mix model vary according to the type of day (day of the week, weekend), and also the specific month. The proposed methodology is applied to a set of real data of the data history of the buildings of the Escuela Politecnica, and the models are validated below with real data during the last six months. The results are crossed with available contextual variables such as, for example, holidays or exam periods, yielding interesting results when studying the real demand in these situations.

Monitorización y evaluación de la habitabilidad, calidad del aire y eficiencia energética de los edificios: experiencias en España, 2020, ISBN 9788412276749, págs. 50-58, 2020

Sustainable Cities and Society, 2020

This paper presents a methodology to improve energy efficiency and hygrothermal comfort condition... more This paper presents a methodology to improve energy efficiency and hygrothermal comfort conditions in public buildings using low-cost ICTs. A change in the daily users`habits is further on suggested. The process develops circularly in four steps: building definition model, monitoring, analysis, and users' participation. The method has been tested in four similar public buildings of traditional construction. Firstly, a building model has been defined (climatology, thermal envelope and maintenance, interior design, systems, and occupancy). Secondly, a lowcost, scalable, and open-source information system has been installed to collect data of energy consumption, temperature, humidity and CO 2 values. The resulting time series were analysed and compared to the energy consumption bills of the previous three years to obtain the real building behaviour. Data gathered by the sensors and suggestions have been made available to users for real-time monitoring. Furthermore, reliable energy indicators to characterize this building typology in services sector have been obtained. Other sub goals include raising awareness among users about the use of public resources, and the initiation of a smart-village strategy using low-cost technologies. The results highlight inefficient consumption patterns and discomfort situation that should encourage users to take action and reorient municipal policies.

Considering the widespread use of mobile robots in different parts of society, it is important to... more Considering the widespread use of mobile robots in different parts of society, it is important to provide them with the capability to behave in a socially acceptable manner. Therefore, a research topic of great importance recently has been the study of Human-Robot Interaction. Autonomous navigation is a fundamental task in Robotics, and several different strategies that produce paths that are either length or time optimized can be found in the literature. However, considering the recent use of mobile robots in a more social context, the use of such classical techniques is restricted. Therefore, in this article we present a social navigation approach considering environments with groups of people. The proposal uses a density function to efficiently represent groups of people, and modify the navigation architecture in order to include the social behaviour of the robot during its motion. This architecture is based on the combined use of the Probabilistic Road Mapping (PRM) and the Rapidly-exploring Random Tree (RRT) path planners and an adaptation of the elastic band algorithm. Experimental evaluation was carried out in different simulated environments, providing insight on the performance of the proposed technique, which surpasses classical techniques with no proxemics awareness in terms of social impact.

Lecture notes in networks and systems, Nov 19, 2022

IOS Press eBooks, Jun 14, 2022

Soon robots will cooperate with humans in everyday tasks. These robots must be endowed with socia... more Soon robots will cooperate with humans in everyday tasks. These robots must be endowed with social skills so that their behavior will be similar to that of people. One of these behaviors is navigation: how the robot plans the route and moves through ubicomp environments. For example, a social behavior during navigation consists of detecting the position of people and evaluating with proxemics those areas where the robot can move and with what velocity. This work presents a new controller for the following ability of a socially aware person. The robot is equipped with RGB-D and laser sensors and navigates through an ubicomp environment that provides the person's position at every moment. The system initially estimates the person's position and its interaction regions at a future instant and then adjusts its path and velocity based on this estimate. Experimental results in simulated environments are included and discussed as initial results to show the performance of this proposal. We include a set of social metrics to validate the proposed results.

Lecture Notes in Computer Science, 2022

Monitorización y evaluación de la habitabilidad, calidad del aire y eficiencia energética de los edificios: experiencias en España, 2020, ISBN 9788412276749, págs. 254-266, 2020

Journal of Physical Agents (JoPha), 2013

During the last six years the RoboComp robotics framework has been steadily growing in the number... more During the last six years the RoboComp robotics framework has been steadily growing in the number of software components, the variety of robots supported and in new solutions to the maintenance of large robotics software repositories. In this paper we present recent advances in the formal definition of the RoboComp component model and a new set of tools based on Domain Specific Languages that have been created to simplify the whole development cycle of the components. Moreover, a new robot simulation tool has been created providing perfect integration with RoboComp and better control over experiments than current existing simulators. Finally, the paper describes a working solution to the important problem of communications middleware independence, which allows users to decide which middleware the components will be compiled with. Our solution has been validated by the integration of Nerve, a novel middleware for critical robotics tasks, in RoboComp.

Journal of Ambient Intelligence and Humanized Computing, Mar 30, 2022