Using physics-like interaction law to perform active environment recognition in mobile robotics
Résumé
In this article, we give some insights of a novel approach to active environment recognition in mobile robotics. The basic idea consists on utilizing a Physics-like interaction law to fix a relation between sensors and effectors values at any time. Our main assumption is that the trajectory of the robot in the phase space, which depends uniquely on its environment -when the law and the nature of the robot are fixed- may discriminate environments better than classical Data Analysis methods. In order to test our assumption, we choose to model an analogical robot which light sensor amplitudes and wheels speed are coupled in a set of differential equations. As a result, we show that our method is tractable and perform well for discriminating simple environments, comparing to a data analysis strategy.
Origine : Fichiers produits par l'(les) auteur(s)