Pasar al contenido principal

DISEÑO DE SISTEMAS ROBOTICOS Y NEUROPROTESICOS PERSONALIZABLES PARA LA ASISTENCIA DE LA MARCHA UTILIZANDO METODOS DE SIMULACION PREDICTIVA

RTI2018-097290-B-C33

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

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

UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

TAILOR: Patient-specific hybrid wearable systems for walking rehabilitation

  • Moreno Sastoque, Juan Camilo
  • Font Llagunes, Josep Maria|||0000-0002-7192-2980
  • del Ama Espinosa, Antonio José
Personalization of robotic exoskeletons for walking assistance to the end user is still a challenge for this technology. The TAILOR project aims to create hybrid and modular robotic-neuroprosthetic wearable systems that can be adapted to an individual patient. For that, a User-Centered Design approach and predictive dynamic simulation tools are conceived to support the design of the hybrid assistive technology., Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Desarrollo de sistemas modulares robóticos y neuroprotésicos personalizables para la asistencia de la marcha patológica a través del diseño centrado en el usuario: Proyecto TAILOR

  • Herrera Valenzuela, Diana Sofía
  • Gil Castillo, Javier
  • Pina, Javier
  • Peiret Giménez, Albert
  • Moreno Sastoque, Juan Camilo
  • Font Llagunes, Josep Maria|||0000-0002-7192-2980
  • Murillo Licea, Narda
  • Gil Agudo, Angel
  • del Ama Espinosa, Antonio José
Currently available wereable exoskeletons and neuroprosthetic gait assistive devices have controverted efficacy and low penetration into rehabilitation centers because they are generic solutions that do not consider the individual requirements and characteristics of each patient. TAILOR project proposes a new approach to the design of customizable neurorobotic systems, based on robotic exoskeletons (WR) and modular neuroprosthetics (NP) to provide subject-specific solutions. These two technologies are integrated with a closed loop hybrid controller. We are using a User-Centered Design approach for the design and development of these technologies to effectively introduce the requirements and needs of patients and clinical staff. Currently, we are making modifications to the WR to integrate it to the NP, which has already been developed, Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Evaluation of optimal control formulations for predicting swing-through axillary crutch-assisted gait

  • Febrer Nafría, Miriam|||0000-0002-1189-835X
  • Manocha, Ranita H.K.
  • Kuntze, Gregor
  • Font Llagunes, Josep Maria|||0000-0002-7192-2980
  • Ronsky, Janet L.
Crutches are widely used to assist gait in individuals with lower limb impairment. Walking with crutches alters both upper and lower body loading, potentially leading to discomfort. As such, it is important to study how crutch walking affects upper and lower extremity movement patterns. Computer modelling and simulation can provide answers that motion analysis cannot. For this reason, the availability of an algorithm that allows the prediction of different crutch walking patterns could be useful in order to study the impact of changing conditions on crutch walking, and could overcome some limitations of experimental studies, such as difficulty in recruiting subjects or limitation in the number of tests that can be performed, Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Modelling neuromusculoskeletal response to functional electrical stimulation

  • Peiret Giménez, Albert
  • Gil Castillo, Javier
  • Pina, Javier
  • Jané Cardona, Marcel
  • Moreno Sastoque, Juan Camilo
  • del Ama Espinosa, Antonio José
  • Font Llagunes, Josep Maria|||0000-0002-7192-2980
A model for functional electrical stimulation with hysteretic muscle recruitment is used to reproduce experimental tibialis anterior stimulation to control ankle dorsiflexion. The subject-specific parameters of the muscle recruitment model where identified from experimental data by solving a nonlinear least-squares problem, Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Rehabilitation of Musculoskeletal Models Using Deep Reinforcement Learning

  • Madorell Batlle, Queralt
  • Peiret Giménez, Albert
  • Font Llagunes, Josep Maria|||0000-0002-7192-2980
Neural rehabilitation is a long and complex process that patients undergo after suffering a nervous system injury, such as stroke. These kinds of injuries usually result in brain cells death and partial loss of mobility and coordination. During rehabilitation, the patient performs a series of movements and physical exercises that promote neural plasticity, the brain’s mechanism to regenerate and make new pathways that substitute the damaged connections. Unfortunately, full recovery is almost impossible. The rehabilitation process is tailored to the patient based on the physician’s expertise, and it evolves with the patient’s needs and recovery. However, few computational models for rehabilitation have been developed. For instance, Lee et al. [1] trained a musculoskeletal model of a healthy subject using deep reinforcement learning, and then a prosthetic leg was added to simulate an injury. Results showed how the artificial neural network that controlled muscle contraction was able to adapt and learn to move with the prosthetic leg. Here we show how deep reinforcement learning can be used to control a musculoskeletal model. The algorithm is able to learn new and stable motions by maximizing the so-called reward function. The nervous system is modelled with an artificial neural network, and the deep deterministic policy gradient (DDPG) algorithm is used to train the model in a simulated environment., Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Assisted Walking with Hybrid Orthosis Using Functional Electrical Stimulation

  • Peiret Giménez, Albert
  • Jané Cardona, Marcel
  • Pàmies Vilà, Rosa|||0000-0002-3814-9199
  • Font Llagunes, Josep Maria|||0000-0002-7192-2980
Neurological disorders affect body mobility, strength and coordination, and can significantly impact the quality of life. For instance, suffering a spinal cord injury (SCI) generally result in permanent lower-limbs paralysis. Robotic assistive devices, such as lower-limb exoskeletons, can help SCI patients to recover their mobility and autonomy in everyday life. Moreover, advances in neuroprosthetics have shown that functional electrical stimulation (FES) can be used to control joint motion by inducing muscle contraction through electrical assistance [1]. Hybrid assistive devices that combine wearable robotics and neuroprosthesis present some advantages compared to robotic assistive devices. Namely, FES-induced muscle contraction activates muscle metabolism, which delays muscle atrophy and promotes cardiovascular activity. However, determining the optimal control strategy of hybrid devices is still a challenge. Here, we present an optimization framework for musculoskeletal models with hybrid assistive devices using the direct collocation method, Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Assisted Walking with Hybrid Orthosis Using Functional Electrical Stimulation

  • Peiret Giménez, Albert
  • Jané Cardona, Marcel
  • Pàmies Vilà, Rosa
  • Font Llagunes, Josep Maria
Neurological disorders affect body mobility, strength and coordination, and can significantly impact the quality of life. For instance, suffering a spinal cord injury (SCI) generally result in permanent lower-limbs paralysis. Robotic assistive devices, such as lower-limb exoskeletons, can help SCI patients to recover their mobility and autonomy in everyday life. Moreover, advances in neuroprosthetics have shown that functional electrical stimulation (FES) can be used to control joint motion by inducing muscle contraction through electrical assistance [1]. Hybrid assistive devices that combine wearable robotics and neuroprosthesis present some advantages compared to robotic assistive devices. Namely, FES-induced muscle contraction activates muscle metabolism, which delays muscle atrophy and promotes cardiovascular activity. However, determining the optimal control strategy of hybrid devices is still a challenge. Here, we present an optimization framework for musculoskeletal models with hybrid assistive devices using the direct collocation method, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

TAILOR: Patient-specific hybrid wearable systems for walking rehabilitation

  • Moreno Sastoque, Juan Camilo
  • Font Llagunes, Josep Maria
  • del Ama Espinosa, Antonio José
Personalization of robotic exoskeletons for walking assistance to the end user is still a challenge for this technology. The TAILOR project aims to create hybrid and modular robotic-neuroprosthetic wearable systems that can be adapted to an individual patient. For that, a User-Centered Design approach and predictive dynamic simulation tools are conceived to support the design of the hybrid assistive technology., Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Rehabilitation of Musculoskeletal Models Using Deep Reinforcement Learning

  • Madorell Batlle, Queralt
  • Peiret Giménez, Albert
  • Font Llagunes, Josep Maria
Neural rehabilitation is a long and complex process that patients undergo after suffering a nervous system injury, such as stroke. These kinds of injuries usually result in brain cells death and partial loss of mobility and coordination. During rehabilitation, the patient performs a series of movements and physical exercises that promote neural plasticity, the brain’s mechanism to regenerate and make new pathways that substitute the damaged connections. Unfortunately, full recovery is almost impossible. The rehabilitation process is tailored to the patient based on the physician’s expertise, and it evolves with the patient’s needs and recovery. However, few computational models for rehabilitation have been developed. For instance, Lee et al. [1] trained a musculoskeletal model of a healthy subject using deep reinforcement learning, and then a prosthetic leg was added to simulate an injury. Results showed how the artificial neural network that controlled muscle contraction was able to adapt and learn to move with the prosthetic leg. Here we show how deep reinforcement learning can be used to control a musculoskeletal model. The algorithm is able to learn new and stable motions by maximizing the so-called reward function. The nervous system is modelled with an artificial neural network, and the deep deterministic policy gradient (DDPG) algorithm is used to train the model in a simulated environment., Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Modelling neuromusculoskeletal response to functional electrical stimulation

  • Peiret Giménez, Albert
  • Gil Castillo, Javier
  • Pina, Javier
  • Jané Cardona, Marcel
  • Moreno Sastoque, Juan Camilo
  • del Ama Espinosa, Antonio José
  • Font Llagunes, Josep Maria
A model for functional electrical stimulation with hysteretic muscle recruitment is used to reproduce experimental tibialis anterior stimulation to control ankle dorsiflexion. The subject-specific parameters of the muscle recruitment model where identified from experimental data by solving a nonlinear least-squares problem, Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Evaluation of optimal control formulations for predicting swing-through axillary crutch-assisted gait

  • Febrer Nafría, Miriam
  • Manocha, Ranita H.K.
  • Kuntze, Gregor
  • Font Llagunes, Josep Maria
  • Ronsky, Janet L.
Crutches are widely used to assist gait in individuals with lower limb impairment. Walking with crutches alters both upper and lower body loading, potentially leading to discomfort. As such, it is important to study how crutch walking affects upper and lower extremity movement patterns. Computer modelling and simulation can provide answers that motion analysis cannot. For this reason, the availability of an algorithm that allows the prediction of different crutch walking patterns could be useful in order to study the impact of changing conditions on crutch walking, and could overcome some limitations of experimental studies, such as difficulty in recruiting subjects or limitation in the number of tests that can be performed, Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Desarrollo de sistemas modulares robóticos y neuroprotésicos personalizables para la asistencia de la marcha patológica a través del diseño centrado en el usuario: Proyecto TAILOR

  • Herrera Valenzuela, Diana Sofía
  • Gil Castillo, Javier
  • Pina, Javier
  • Peiret Giménez, Albert
  • Moreno Sastoque, Juan Camilo
  • Font Llagunes, Josep Maria
  • Murillo Licea, Narda
  • Gil Agudo, Angel
  • del Ama Espinosa, Antonio José
Currently available wereable exoskeletons and neuroprosthetic gait assistive devices have controverted efficacy and low penetration into rehabilitation centers because they are generic solutions that do not consider the individual requirements and characteristics of each patient. TAILOR project proposes a new approach to the design of customizable neurorobotic systems, based on robotic exoskeletons (WR) and modular neuroprosthetics (NP) to provide subject-specific solutions. These two technologies are integrated with a closed loop hybrid controller. We are using a User-Centered Design approach for the design and development of these technologies to effectively introduce the requirements and needs of patients and clinical staff. Currently, we are making modifications to the WR to integrate it to the NP, which has already been developed, Peer Reviewed, Objectius de Desenvolupament Sostenible::3 - Salut i Benestar, Postprint (author's final draft)