An Ontology-based approach for Robot and Ambient System collaboration
Abstract
In activity recognition, sensor based errors or uncertainties induce a wrong statement in the environment representation. To overcome these issues we introduce our ontology-based approach where a system, based on a mobile robot and an ambient system, is able to generate collaborative tasks when necessary to recognize activities. Using two ontolo-gies to represent the environment, inconsistencies are detected and high level data are exchanged between both systems to correct and clarify ambiguous description of the environment. This process allows to generate adequate clarifying tasks by explicitly including knowledge and capabilities of each system. We expose our approach in two experiments where interaction between both systems are mandatory to respond a human "find an object" request in a first scenario and recognize multi user activities in a second scenario.
Domains
Computer Science [cs] Artificial Intelligence [cs.AI] Computer Science [cs] Signal and Image Processing Computer Science [cs] Computer Vision and Pattern Recognition [cs.CV] Computer Science [cs] Robotics [cs.RO] Cognitive science Computer science Cognitive science Psychology Cognitive science Neuroscience
Fichier principal
ontology-based-approach-for-robot-and-ambient-system-collaboration.pdf (515.82 Ko)
Télécharger le fichier
Origin : Files produced by the author(s)
Loading...