Home /Research /Deep State Representation: an unified internal representation for the robotics cognitive architecture CORTEX
OTHER

Deep State Representation: an unified internal representation for the robotics cognitive architecture CORTEX

Calderita Estévez, Luis Prez Vicente

Year
2016
Citations
9

Abstract

espanolCORTEX propone una arquitectura basada en agentes donde estos se encargan de las habilidades clasicas, como la percepcion, la actuacion y la planificacion. Los agentes deben ser autonomos y obedientes, y estan a cargo de una funcionalidad bien definida ---ya sea deliberativa, reactiva o hibrida---. Entre ellos se comunican a traves de una estructura de datos dinamica compartida denominada �Deep State Representation�. Esta Tesis se centra en el desarrollo de �Deep State Representation�. El objetivo que se persigue es encontrar el diseno de un grafo dirigido dinamico multi---etiquetado que pueda contener varios niveles de abstraccion abarcando, desde la geometria basica y el estado sensorial, a los simbolos de alto nivel y predicados, y que juntos describan el estado del robot y del entorno durante un corto espacio de tiempo. La recien nacida arquitectura robotica cognitiva CORTEX puede ser dibujada como una superficie cilindrica, dividida en varias rodajas verticales que representan a los agentes. En el centro del cilindro, la nueva estructura de datos contiene la creencia interna actual del robot, afectando y siendo afectada por todos los agentes, y siempre luchando por mantener un equilibrio que la realidad se empena en desvanecer. EnglishCORTEX proposes a agent---based architecture, where the agents are in charge of classical perceptual, actuation and planning abilities. The agents should be autonomous and obedient, and they are in charge of a well defined functionally --- whether it be reactive, deliberative of hybrid---. They communicate through a shared data structure called Deep State Representation. This Thesis focuses on the developing of Deep State Representation. The goal that is pursued seeks the design of a multi---labelled dynamic graph object that can hold several levels of abstraction, from basic geometry and sensorial state to high---level symbols and predicates describing the state of the robot and the environment during a short time lapse. The final view of the new robotics cognitive architecture CORTEX can be seen as cylindrical surface splitted in several vertical slices, which are the agents. In the centre of the cylinder, the new data structure holds the current internal belief of the robot, affecting and being affected by all the agents, and always struggling for an equilibrium that the reality fades away.

Keywords

HumanitiesCartographyRepresentation (politics)ArtGeographyPolitical science

Related papers

Browse all OTHER papers