Person: Calvo Tapia, Carlos
Loading...
First Name
Carlos
Last Name
Calvo Tapia
Affiliation
Universidad Complutense de Madrid
Faculty / Institute
Ciencias Biológicas
Department
Biodiversidad, Ecología y Evolución
Area
Matemática Aplicada
Identifiers
5 results
Search Results
Now showing 1 - 5 of 5
Item Cognitive Neural Network Driving DoF-Scalable Limbs in Time-Evolving Situations(2018) Calvo Tapia, Carlos; Villacorta Atienza, José Antonio; Kastalskiy, Innokentiy; Díez Hermano, Sergio; Sánchez Jiménez, Abel; Makarov Slizneva, ValeriyObject handling and manipulation are vital skills for humans and autonomous humanoid robots. The fundamental bases of how our brain solves such tasks remain largely unknown. Here we develop a novel approach that addresses the problem of limb movements in time-evolving situations at an abstract cognitive level. We exploit the concept of generalized cognitive maps constructed in the so-called handspace by a neural network simulating a wave simultaneously exploring different subject actions independently on the number of objects in the workspace. We show that the approach is scalable to limbs with minimalistic and redundant numbers of degrees of freedom (DoF). It also allows biasing the effort of reaching a target among different DoF.Item ¿Es la biomimética el futuro de la robótica?(Boletín del Ilustre Colegio Oficial de Doctores y Licenciados en Filosofía y Letras y en Ciencias, 2016) Makarov Slizneva, Valeriy; Villacorta Atienza, José Antonio; Calvo Tapia, CarlosAntes de que a principios del siglo XX el concepto de robot fuera introducido en nuestra cultura tal y como hoy lo concebimos, el hombre llevaba mucho tiempo persiguiendo el sueño de crear ‘humanos artificiales’. Autómatas capaces de tocar instrumentos, bailar o incluso jugar al ajedrez fueron desarrollados para el divertimento y asombro del público. Sin embargo, la tecnificación de nuestra sociedad nos ha llevado, más que a desear, a demandar robots capaces de realizar eficazmente numerosas tareas y sustituirnos así en situaciones tediosas, pesadas o peligrosas. Los espectaculares avances tecnológicos producidos en la segunda mitad del pasado siglo condujeron a una nueva era de conocimiento en la que la computación se erigía como una nueva piedra filosofal. Si bien así fue para numerosas disciplinas científicas, hoy en día la robótica no ha alcanzado las cotas que entonces se esperaban, y todavía no existen robots capaces de realizar siquiera las tareas más sencillas de forma realmente autónoma, como por ejemplo ir a la cocina, recoger platos y lavarlos.Item El GPS dinámico del cerebro nos acerca al diseño de robots inteligentes(Red.escubre, 2015) Makarov Slizneva, Valeriy; Calvo Tapia, Carlos; Villacorta Atienza, José AntonioEnseñar a un robot a jugar al ajedrez es incomparablemente más fácil que conseguir que sea capaz de jugar al fútbol o moverse entre la muchedumbre de una céntrica calle de Madrid. Diseñar un robot inteligente, capaz de imitar nuestras habilidades sensoriales y motoras, pasa por comprender cómo entiende el cerebro nuestra realidad, tan cambiante y compleja.Item Semantic Knowledge Representation for Strategic Interactions in Dynamic Situations(Frontiers in Neurorobotics, 2020) Calvo Tapia, Carlos; Villacorta Atienza, José Antonio; Díez Hermano, Sergio; Khoruzkho, Maxim; Lobov, Sergey; Potapov, Ivan; Sánchez Jiménez, Abel; Makarov Slizneva, ValeriyEvolved living beings can anticipate the consequences of their actions in complex multilevel dynamic situations. This ability relies on abstracting the meaning of an action. The underlying brain mechanisms of such semantic processing of information are poorly understood. Here we show how our novel concept, known as time compaction, provides a natural way of representing semantic knowledge of actions in time-changing situations. As a testbed, we model a fencing scenario with a subject deciding between attack and defense strategies. The semantic content of each action in terms of lethality, versatility, and imminence is then structured as a spatial (static) map representing a particular fencing (dynamic) situation. The model allows deploying a variety of cognitive strategies in a fast and reliable way. We validate the approach in virtual reality and by using a real humanoid robot.Item Limb Movement in Dynamic Situations Based on Generalized Cognitive Maps(Mathematical Modelling of Natural Phenomena, 2017) Villacorta Atienza, José Antonio; Calvo Tapia, Carlos; Lobov, S.; Makarov Slizneva, ValeriyThe fundamental bases of how our brain solves different tasks of object manipulation remain largely unknown. Here we consider the problem of the limb movement in dynamic situations on an abstract cognitive level and propose a novel approach relying on: i) transformation of the problem from the limb workspace to the so-called hand-space, and ii) construction of a generalized cognitive map (GCM) in the hand-space. The GCM provides a trajectory that can be followed by the limb, which ensures an efficient collision-free movement and target catching in the workspace. Our numerical simulations confirm the approach feasibility but also reveal the problem complexity. We then validate the GCM-based solutions in real-life scenarios. We show that a GCM-equipped humanoid robot can catch a fly ball in a similar way as a human subject does. The static nature of the GCMs enables learning and automation of sophisticated cognitive behaviors exhibited by humans.