APRENDIZAJE DE AFFORDANCS PARA EL CONTROL DE ROBOTS POR INTENCIONES
ONE OF THE MAIN SOCIAL CHALLENGES IN THE NEAR FUTURE FOR THE SPANISH SOCIETY IS TO FACE THE INCREASE OF DEPENDENT PEOPLE DUE TO AGING OR ILLNESS. ACCORDING TO INE STATISTICS, ONE PER CENT OF THE POPULATION SUFFER IMPAIRMENTS RELAT...
ver más
Descripción del proyecto
ONE OF THE MAIN SOCIAL CHALLENGES IN THE NEAR FUTURE FOR THE SPANISH SOCIETY IS TO FACE THE INCREASE OF DEPENDENT PEOPLE DUE TO AGING OR ILLNESS. ACCORDING TO INE STATISTICS, ONE PER CENT OF THE POPULATION SUFFER IMPAIRMENTS RELATED TO THE MOTOR SYSTEM AND OVER 400.000 PEOPLE HAVE SOME TYPE OF LIMITATION ON THE UPPER LIMB. ROBOTICS IS ONE OF THE MOST PROMISING TECHNOLOGIES TO IMPROVE THE QUALITY OF LIVE OF IMPAIRED PEOPLE, SINCE ROBOTS CAN HELP TO RESTORE OR SUBSTITUTE MOTOR FUNCTIONS. THE LONG-TERM VISION OF SUCH A SYSTEM WOULD BE A ROBOTIC DEVICE CONTROLLED BY THE USER IN A NATURAL WAY TO EXECUTE DAILY ACTIONS. FOR CERTAIN TARGET POPULATIONS WITH SEVERE MOTOR IMPAIRMENTS, BRAIN-COMPUTER INTERFACES (BCI) SEEM THE MOST APPROPRIATE INTERFACE. UNFORTUNATELY, THE CONTROL OF A ROBOTIC ARM WITH A BCI INTERFACE IS STILL AN OPEN CHALLENGE. IN THIS CONTEXT, THE OBJECTIVE OF LAICO IS TO EQUIP A ROBOTIC ARM WITH THE REQUIRED A PRIORI KNOWLEDGE EMBEDDED IN EVERY DAY TASKS THAT ALLOW A SEAMLESS INTERACTION WITH A HUMAN USING A NON-INVASIVE BCI. THE PROJECT DRAWS INSPIRATION FROM HUMAN MOTOR CONTROL WHICH, ACCORDING TO NEUROSCIENCE STUDIES, RESULTS FROM THE INTERPLAY OF TWO FUNCTIONALLY SEPARABLE SYSTEMS: AN INTENTIONAL SYSTEM THAT IMPLEMENTS THE GOALS AND INTENTIONS AND AN ENVIRONMENTALLY-GUIDED EXECUTION SYSTEM THAT CONTROLS THE INTERACTION WITH THE ENVIRONMENT. THE KEY NOVELTY OF THE PROJECT IS TO USE THIS TWO-LEVEL ARCHITECTURE WITH AN INTELLIGENT ARM THAT INTERPRETS THE ENVIRONMENT IN A SIMILAR WAY TO THE EXECUTION LEVEL IN HUMANS. ONE SUCH A SYSTEM WILL CREATE AN IMPLICIT COMMUNICATION CHANNEL THROUGH THE ENVIRONMENT PROPERTIES THAT WILL IN TURN SIMPLIFY THE CONTROL OF THE ROBOT BY RELYING ON ITS OWN LEARNED BEHAVIORS TO SOLVE THE TASKS. THE MAIN CHALLENGES OF THE PROJECT ARE: 1) TO DEVELOP THE MODELS AND LEARNING ALGORITHMS THAT WILL INTERPRET THE ENVIRONMENT IN TERMS OF ROBOT ACTIONS AND CONSEQUENCES, A.K.A. AFFORDANCES; 2) TO DEVELOP MOTION PRIMITIVES THAT ALLOW TO EXPLOIT THIS AFFORDANCE KNOWLEDGE; AND 3) TO CREATE AN INTENTIONAL LEVEL BASED ON A BCI SYSTEM TO SPECIFY THE GOALS AND INTENTIONS OF THE USER AND EXPLOIT THE ROBOTIC DEVICE. TO ILLUSTRATE THE ADVANTAGES OF SUCH A SCHEME, LAICO WILL BUILD A FULLY OPERATIONAL PROTOTYPE OF A BRAIN-CONTROLLED ROBOTIC ARM BASED ON THE TWO LEVEL ARCHITECTURE. THE DEMONSTRATOR WILL BE ABLE TO OPERATE IN REALISTIC CONDITIONS TO EXECUTE SIMPLE EVERY DAY TASKS SUCH AS POURING WATER OR ANSWERING THE PHONE WHILE CONTROLLED THROUGH THE BCI SYSTEM. THE PROJECT FOLLOWS A TYPE A PROJECT FOR YOUNG RESEARCHERS AND ESTABLISHES A NEW LINE OF RESEARCH WITHIN THE ROBOTICS, PERCEPTION AND REAL TIME GROUP AT THE UNIVERSITY OF ZARAGOZA. IT CONTINUES THE RESEARCH ACTIVITIES STARTED BY THE PRINCIPAL INVESTIGATOR WHILE WORKING FOR THREE YEARS AS A RESEARCHER AT THE INSTITUTO SUPERIOR TECNICO IN LISBON. THE RESEARCH TEAM COMBINES THE EXPERTISE AND KNOWLEDGE OF FOUR DIFFERENT INSTITUTIONS THE ROBOTICS GROUP AT THE UNIVERSITY OF ZARAGOZA, THE CENTRO UNIVERSITARIO DE LA DEFENSA OF ZARAGOZA, THE INRIA IN BORDEAUX, FRANCE AND THE MAX-PLANK INSTITUTE IN TUBINGEN, GERMANY. THE SYNERGY OF THE MEMBERS OF THE TEAM IS A KEY ASSET OF THE PROPOSAL, SINCE THEY HAVE BEEN ACTIVELY COLLABORATING DURING THE LAST YEARS ON THE FIELDS OF ROBOT LEARNING AND HUMANOID ROBOTS, BAYESIAN STATISTICS, REINFORCEMENT LEARNING AND CONTROL PROBLEMS. PRENDIZAJE AUTOMATICO\ROBOTS INTELIGENTES
Seleccionando "Aceptar todas las cookies" acepta el uso de cookies para ayudarnos a brindarle una mejor experiencia de usuario y para analizar el uso del sitio web. Al hacer clic en "Ajustar tus preferencias" puede elegir qué cookies permitir. Solo las cookies esenciales son necesarias para el correcto funcionamiento de nuestro sitio web y no se pueden rechazar.
Cookie settings
Nuestro sitio web almacena cuatro tipos de cookies. En cualquier momento puede elegir qué cookies acepta y cuáles rechaza. Puede obtener más información sobre qué son las cookies y qué tipos de cookies almacenamos en nuestra Política de cookies.
Son necesarias por razones técnicas. Sin ellas, este sitio web podría no funcionar correctamente.
Son necesarias para una funcionalidad específica en el sitio web. Sin ellos, algunas características pueden estar deshabilitadas.
Nos permite analizar el uso del sitio web y mejorar la experiencia del visitante.
Nos permite personalizar su experiencia y enviarle contenido y ofertas relevantes, en este sitio web y en otros sitios web.