IRI - Institut de Robòtica i Informàtica Industrial, CSIC-UPC
http://hdl.handle.net/2117/2249
2024-03-28T16:40:49Z
2024-03-28T16:40:49Z
Introducing social robots to assess frailty in older adults
Civit Bertran, Aniol
Andriella, Antonio
Barrué Subirana, Cristian
Antonio, Maite
Boqué, Concepción
Alenyà Ribas, Guillem
http://hdl.handle.net/2117/405169
2024-03-22T13:10:14Z
2024-03-22T13:03:01Z
Introducing social robots to assess frailty in older adults
Civit Bertran, Aniol; Andriella, Antonio; Barrué Subirana, Cristian; Antonio, Maite; Boqué, Concepción; Alenyà Ribas, Guillem
Frailty is a crucial indicator in determining the well-being of older adults in terms of their health. With the growing number of elderly people, the demand for geriatricians is increasing, which means that they have less time to spend with each patient. The current methods for frailty assessment use simple tests that are time-consuming and do not require specific medical expertise. To address this issue, this paper proposes the use of social robots to assess frailty autonomously. It presents a practical proposal that defines the robot’s behavior and explains the design and implementation concepts. Finally, it discusses some of the challenges that may arise from introducing social robots as frailty evaluators.
2024-03-22T13:03:01Z
Civit Bertran, Aniol
Andriella, Antonio
Barrué Subirana, Cristian
Antonio, Maite
Boqué, Concepción
Alenyà Ribas, Guillem
Frailty is a crucial indicator in determining the well-being of older adults in terms of their health. With the growing number of elderly people, the demand for geriatricians is increasing, which means that they have less time to spend with each patient. The current methods for frailty assessment use simple tests that are time-consuming and do not require specific medical expertise. To address this issue, this paper proposes the use of social robots to assess frailty autonomously. It presents a practical proposal that defines the robot’s behavior and explains the design and implementation concepts. Finally, it discusses some of the challenges that may arise from introducing social robots as frailty evaluators.
Adaptive human-robot collaboration: evolutionary learning of action costs using an action outcome simulator
Izquierdo Badiola, Silvia
Alenyà Ribas, Guillem
Rizzo, Carlos
http://hdl.handle.net/2117/404936
2024-03-19T13:00:19Z
2024-03-19T12:53:11Z
Adaptive human-robot collaboration: evolutionary learning of action costs using an action outcome simulator
Izquierdo Badiola, Silvia; Alenyà Ribas, Guillem; Rizzo, Carlos
One of the main challenges for successful human- robot collaborative applications lies in adapting the plan to the human agent’s changing state and preferences. A promising solution is to bridge the gap between agent modelling and AI task planning, which can be done by integrating the agent state as action costs in the task planning domain. This allows for the plan to be adapted to different partners, by influencing the action allocation. The difficulty then lies in setting appropriate action costs. This paper presents a novel framework to learn a set of planning action costs considering the preferred actions for an agent based on their state. An evolutionary optimisation algorithm is used for this purpose, and an action outcome simulator is developed to act as the black-box function, based on both an agent model and an action type model. This addresses the challenge of collecting data in HRC real-world scenarios, accelerating the learning for posterior fine-tuning in real applications. The coherence of the models and the simulator is proven through a conducted survey, and the learning algorithm is shown to learn appropriate action costs, producing plans that satisfy both the agents’ preferences and the prioritised plan requisites. The resulting system is a generic learning framework integrating components that can be easily extended to a wide range of applications, models and planning formalisms.
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
2024-03-19T12:53:11Z
Izquierdo Badiola, Silvia
Alenyà Ribas, Guillem
Rizzo, Carlos
One of the main challenges for successful human- robot collaborative applications lies in adapting the plan to the human agent’s changing state and preferences. A promising solution is to bridge the gap between agent modelling and AI task planning, which can be done by integrating the agent state as action costs in the task planning domain. This allows for the plan to be adapted to different partners, by influencing the action allocation. The difficulty then lies in setting appropriate action costs. This paper presents a novel framework to learn a set of planning action costs considering the preferred actions for an agent based on their state. An evolutionary optimisation algorithm is used for this purpose, and an action outcome simulator is developed to act as the black-box function, based on both an agent model and an action type model. This addresses the challenge of collecting data in HRC real-world scenarios, accelerating the learning for posterior fine-tuning in real applications. The coherence of the models and the simulator is proven through a conducted survey, and the learning algorithm is shown to learn appropriate action costs, producing plans that satisfy both the agents’ preferences and the prioritised plan requisites. The resulting system is a generic learning framework integrating components that can be easily extended to a wide range of applications, models and planning formalisms.
Model predictive control of urban drainage systems considering uncertainty
Lorenz Svensen, Jan
Sun, Congcong
Cembrano Gennari, Gabriela
Puig Cayuela, Vicenç
http://hdl.handle.net/2117/404007
2024-03-11T00:15:05Z
2024-03-08T13:37:01Z
Model predictive control of urban drainage systems considering uncertainty
Lorenz Svensen, Jan; Sun, Congcong; Cembrano Gennari, Gabriela; Puig Cayuela, Vicenç
This brief contributes to the application of model predictive control (MPC) to address the combined sewer overflow (CSO) problem in urban drainage systems (UDSs) with uncertainty. In UDS, dealing with uncertainty in rain forecast and dynamic models is crucial due to the possible impact on the UDS control performance. Two different MPC approaches are considered: tube-based MPC (T-MPC) and chance-constrained MPC (CC-MPC), which represent uncertainty in deterministic and stochastic manners, respectively. This brief presents how to apply T-MPC to UDS, by establishing a mathematical relation with CC-MPC, and a rigorous mathematical comparison. Based on simulations using the Astlingen benchmark UDS, the strengths and weaknesses of the performance of T-MPC and CC-MPC in UDS were compared. Differences in the involved mathematical computations have also been analyzed. Moreover, the comparison in performance also indicates the applicability of each MPC approach in different uncertainty scenarios.
© 2023 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
2024-03-08T13:37:01Z
Lorenz Svensen, Jan
Sun, Congcong
Cembrano Gennari, Gabriela
Puig Cayuela, Vicenç
This brief contributes to the application of model predictive control (MPC) to address the combined sewer overflow (CSO) problem in urban drainage systems (UDSs) with uncertainty. In UDS, dealing with uncertainty in rain forecast and dynamic models is crucial due to the possible impact on the UDS control performance. Two different MPC approaches are considered: tube-based MPC (T-MPC) and chance-constrained MPC (CC-MPC), which represent uncertainty in deterministic and stochastic manners, respectively. This brief presents how to apply T-MPC to UDS, by establishing a mathematical relation with CC-MPC, and a rigorous mathematical comparison. Based on simulations using the Astlingen benchmark UDS, the strengths and weaknesses of the performance of T-MPC and CC-MPC in UDS were compared. Differences in the involved mathematical computations have also been analyzed. Moreover, the comparison in performance also indicates the applicability of each MPC approach in different uncertainty scenarios.
Eduquem les criatures... també les artificials!
Torras, Carme
http://hdl.handle.net/2117/403038
2024-02-23T12:40:14Z
2024-02-23T12:38:15Z
Eduquem les criatures... també les artificials!
Torras, Carme
Artificial és tot allò creat pels humans, ja siguin objectes d’artesania com enginys fruit de la tecnologia. Malgrat l’antiguitat dels productes artificials i de la utilització d’eines per construir-los, no és fins a principis del segle XX que filòsofs com Martin Heidegger comencen a reflexionar sobre el que anomenen “l’era de la tècnica”.
2024-02-23T12:38:15Z
Torras, Carme
Artificial és tot allò creat pels humans, ja siguin objectes d’artesania com enginys fruit de la tecnologia. Malgrat l’antiguitat dels productes artificials i de la utilització d’eines per construir-los, no és fins a principis del segle XX que filòsofs com Martin Heidegger comencen a reflexionar sobre el que anomenen “l’era de la tècnica”.
Desplegament ètic de la robòtica assistencial per a un envelliment saludable i sostenible
Torras, Carme
http://hdl.handle.net/2117/403032
2024-02-23T12:20:13Z
2024-02-23T12:19:08Z
Desplegament ètic de la robòtica assistencial per a un envelliment saludable i sostenible
Torras, Carme
En capítols anteriors s’ha parlat de l’envelliment des del punt de vista mèdic i farmacològic; aquí s'abordarà des del punt de vista tecnològic. Es descriuran tecnologies que poden ajudar els cuidadors a tenir cura de les persones grans d’una manera saludable i sostenible en un context d’augment constant d’aquesta part de la població. En concret, es presentaran dos prototips de robots assistencials, un d'ajuda a menjar i l'altre d'entrenament cognitiu, ambdós co-dissenyats amb institucions sanitàries. També s'exposaran les qüestions ètiques suscitades pel desplegament d'aquestes tecnologies i les iniciatives de formació en tecnoètica que han sorgit, algunes de les quals aprofiten l'atractiu de la narrativa de ciència-ficció.
2024-02-23T12:19:08Z
Torras, Carme
En capítols anteriors s’ha parlat de l’envelliment des del punt de vista mèdic i farmacològic; aquí s'abordarà des del punt de vista tecnològic. Es descriuran tecnologies que poden ajudar els cuidadors a tenir cura de les persones grans d’una manera saludable i sostenible en un context d’augment constant d’aquesta part de la població. En concret, es presentaran dos prototips de robots assistencials, un d'ajuda a menjar i l'altre d'entrenament cognitiu, ambdós co-dissenyats amb institucions sanitàries. També s'exposaran les qüestions ètiques suscitades pel desplegament d'aquestes tecnologies i les iniciatives de formació en tecnoètica que han sorgit, algunes de les quals aprofiten l'atractiu de la narrativa de ciència-ficció.
Collocation methods for second and higher order systems
Moreno Martín, Siro
Ros Giralt, Lluís
Celaya Llover, Enric
http://hdl.handle.net/2117/402641
2024-02-26T00:30:54Z
2024-02-22T11:12:58Z
Collocation methods for second and higher order systems
Moreno Martín, Siro; Ros Giralt, Lluís; Celaya Llover, Enric
It is often unnoticed that the predominant way to use collocation methods is fundamentally flawed when applied to optimal control in robotics.
Such methods assume that the system dynamics is given by a first order ODE, whereas robots are often governed by a second or higher order ODE involving configuration variables and their time derivatives. To apply a collocation method, therefore, the usual practice is to resort to the well known procedure of casting an Mth order ODE into M first order ones. This manipulation, which in the continuous domain is perfectly valid, leads to inconsistencies when the problem is discretized. Since the configuration variables and their time derivatives are approximated with polynomials of the same degree, their differential dependencies cannot be fulfilled, and the actual dynamics is not satisfied, not even at the collocation points. This paper draws attention to this problem, and develops improved versions of the trapezoidal and Hermite-Simpson collocation methods that do not present these inconsistencies. In many cases, the new methods reduce the dynamic transcription error in one order of magnitude, or even more, without noticeably increasing the cost of computing the solutions.
2024-02-22T11:12:58Z
Moreno Martín, Siro
Ros Giralt, Lluís
Celaya Llover, Enric
It is often unnoticed that the predominant way to use collocation methods is fundamentally flawed when applied to optimal control in robotics.
Such methods assume that the system dynamics is given by a first order ODE, whereas robots are often governed by a second or higher order ODE involving configuration variables and their time derivatives. To apply a collocation method, therefore, the usual practice is to resort to the well known procedure of casting an Mth order ODE into M first order ones. This manipulation, which in the continuous domain is perfectly valid, leads to inconsistencies when the problem is discretized. Since the configuration variables and their time derivatives are approximated with polynomials of the same degree, their differential dependencies cannot be fulfilled, and the actual dynamics is not satisfied, not even at the collocation points. This paper draws attention to this problem, and develops improved versions of the trapezoidal and Hermite-Simpson collocation methods that do not present these inconsistencies. In many cases, the new methods reduce the dynamic transcription error in one order of magnitude, or even more, without noticeably increasing the cost of computing the solutions.
Robótica assistencial: una aposta per l'envelliment saludable i sostenible
Torras, Carme
http://hdl.handle.net/2117/402102
2024-02-16T13:40:10Z
2024-02-16T13:38:24Z
Robótica assistencial: una aposta per l'envelliment saludable i sostenible
Torras, Carme
La població de més de 65 anys ha augmentat de manera progressiva en les darreres dècades i els estudis prospectius avisen que continuarà creixent de manera cada vegada més accelerada. La tecnologia pot contribuir tant a la prevenció com a la realització de tasques assistencials rutinàries. En particular, la robòtica assistencial destaca com un element decisiu per a construir un futur amb un envelliment saludable i sostenible, però cal que el seu desplegament es faci d’acord amb principis ètics, que sigui supervisat per òrgans competents i que la formació s’estengui a tots els agents implicats.
2024-02-16T13:38:24Z
Torras, Carme
La població de més de 65 anys ha augmentat de manera progressiva en les darreres dècades i els estudis prospectius avisen que continuarà creixent de manera cada vegada més accelerada. La tecnologia pot contribuir tant a la prevenció com a la realització de tasques assistencials rutinàries. En particular, la robòtica assistencial destaca com un element decisiu per a construir un futur amb un envelliment saludable i sostenible, però cal que el seu desplegament es faci d’acord amb principis ètics, que sigui supervisat per òrgans competents i que la formació s’estengui a tots els agents implicats.
Humans i robots: ¿qui modela qui?
Torras, Carme
http://hdl.handle.net/2117/402087
2024-02-16T10:40:15Z
2024-02-16T10:35:25Z
Humans i robots: ¿qui modela qui?
Torras, Carme
En un futur ben proper, els robots socials, que avui són objecte d’intensa investigació, sens dubte ens modelaran. Individualment i com a societat. Això ens obliga a preparar-nos per respondre moltes qüestions, principalment relacionades amb l’ètica.
2024-02-16T10:35:25Z
Torras, Carme
En un futur ben proper, els robots socials, que avui són objecte d’intensa investigació, sens dubte ens modelaran. Individualment i com a societat. Això ens obliga a preparar-nos per respondre moltes qüestions, principalment relacionades amb l’ètica.
A hybrid control-oriented PEMFC model based on echo state networks and gaussian radial basis functions
Aguilar Plazaola, José Agustín
Chanal, Damien
Chamagne, Didier
Yousfi-Steiner, Nadia
Péra, Marie-Cécile
Husar, Attila Peter
Andrade-Cetto, Juan
http://hdl.handle.net/2117/401910
2024-02-18T21:55:49Z
2024-02-14T13:01:04Z
A hybrid control-oriented PEMFC model based on echo state networks and gaussian radial basis functions
Aguilar Plazaola, José Agustín; Chanal, Damien; Chamagne, Didier; Yousfi-Steiner, Nadia; Péra, Marie-Cécile; Husar, Attila Peter; Andrade-Cetto, Juan
The goal of increasing efficiency and durability of fuel cells can be achieved through optimal control of their operating conditions. In order to implement such controllers, accurate and computationally efficient fuel cell models must be developed. This work presents a hybrid (physics-based and data-driven), control-oriented model for approximating the output voltage of proton exchange membrane fuel cells (PEMFCs) while operating under dynamical conditions. First, a physics-based model, built from simplified electrochemical, membrane dynamics and mass conservation equations, is developed and validated through experimental data. Second, a data-driven, neural network (echo state network) is trained, fitted and tested with the same dataset. Then, the hybrid model is formed as a parallel structure, where the simplified physics-based model and the trained data-driven model are merged through an algorithm based on Gaussian radial basis functions. The merging algorithm compares the output of both single models and assigns weights for computing the prediction of the hybrid result. The proposed hybrid model structure is successfully trained, validated and tested with an experimental dataset originating from fuel cells within an automotive PEMFC stack. The hybrid model is assessed through the mean square error index, with the result of a low tracking error.
2024-02-14T13:01:04Z
Aguilar Plazaola, José Agustín
Chanal, Damien
Chamagne, Didier
Yousfi-Steiner, Nadia
Péra, Marie-Cécile
Husar, Attila Peter
Andrade-Cetto, Juan
The goal of increasing efficiency and durability of fuel cells can be achieved through optimal control of their operating conditions. In order to implement such controllers, accurate and computationally efficient fuel cell models must be developed. This work presents a hybrid (physics-based and data-driven), control-oriented model for approximating the output voltage of proton exchange membrane fuel cells (PEMFCs) while operating under dynamical conditions. First, a physics-based model, built from simplified electrochemical, membrane dynamics and mass conservation equations, is developed and validated through experimental data. Second, a data-driven, neural network (echo state network) is trained, fitted and tested with the same dataset. Then, the hybrid model is formed as a parallel structure, where the simplified physics-based model and the trained data-driven model are merged through an algorithm based on Gaussian radial basis functions. The merging algorithm compares the output of both single models and assigns weights for computing the prediction of the hybrid result. The proposed hybrid model structure is successfully trained, validated and tested with an experimental dataset originating from fuel cells within an automotive PEMFC stack. The hybrid model is assessed through the mean square error index, with the result of a low tracking error.
Heteroscedastic Gaussian processes and random features: scalable motion primitives with guarantees
Caldarelli, Edoardo
Chatalic, Antoine
Colomé Figueras, Adrià
Rosasco, Lorenzo
Torras, Carme
http://hdl.handle.net/2117/401855
2024-02-18T09:12:51Z
2024-02-14T09:48:41Z
Heteroscedastic Gaussian processes and random features: scalable motion primitives with guarantees
Caldarelli, Edoardo; Chatalic, Antoine; Colomé Figueras, Adrià; Rosasco, Lorenzo; Torras, Carme
Heteroscedastic Gaussian processes (HGPs) are kernel-based, non-parametric models that can be used to infer nonlinear functions with time-varying noise. In robotics, they can be employed for learning from demonstration as motion primitives, i.e. as a model of the trajectories to be executed by the robot. HGPs provide variance estimates around the reference signal modeling the trajectory, capturing both the predictive uncertainty and the motion variability. However, similarly to standard Gaussian processes they suffer from a cubic complexity in the number of training points, due to the inversion of the kernel matrix. The uncertainty can be leveraged for more complex learning tasks, such as inferring the variable impedance profile required from a robotic manipulator. However, suitable approximations are needed to make HGPs scalable, at the price of potentially worsening the posterior mean and variance profiles. Motivated by these observations, we study the combination of HGPs and random features, which are a popular, data-independent approximation strategy of kernel functions. In a theoretical analysis, we provide novel guarantees on the approximation error of the HGP posterior due to random features. Moreover, we validate this scalable motion primitive on real robot data, related to the problem of variable impedance learning. In this way, we show that random features offer a viable and theoretically sound alternative for speeding up the trajectory processing, without sacrificing accuracy.
2024-02-14T09:48:41Z
Caldarelli, Edoardo
Chatalic, Antoine
Colomé Figueras, Adrià
Rosasco, Lorenzo
Torras, Carme
Heteroscedastic Gaussian processes (HGPs) are kernel-based, non-parametric models that can be used to infer nonlinear functions with time-varying noise. In robotics, they can be employed for learning from demonstration as motion primitives, i.e. as a model of the trajectories to be executed by the robot. HGPs provide variance estimates around the reference signal modeling the trajectory, capturing both the predictive uncertainty and the motion variability. However, similarly to standard Gaussian processes they suffer from a cubic complexity in the number of training points, due to the inversion of the kernel matrix. The uncertainty can be leveraged for more complex learning tasks, such as inferring the variable impedance profile required from a robotic manipulator. However, suitable approximations are needed to make HGPs scalable, at the price of potentially worsening the posterior mean and variance profiles. Motivated by these observations, we study the combination of HGPs and random features, which are a popular, data-independent approximation strategy of kernel functions. In a theoretical analysis, we provide novel guarantees on the approximation error of the HGP posterior due to random features. Moreover, we validate this scalable motion primitive on real robot data, related to the problem of variable impedance learning. In this way, we show that random features offer a viable and theoretically sound alternative for speeding up the trajectory processing, without sacrificing accuracy.