2011 | OriginalPaper | Buchkapitel
On the Implementation of a Theory of Perceptual Mapping
verfasst von : Wai Kiang Yeap, M. Zulfikar Hossain, Thomas Brunner
Erschienen in: AI 2011: Advances in Artificial Intelligence
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
A recent theory of perceptual mapping argues that humans do not integrate successive views using a mathematical transformation approach to form a perceptual map. Rather, it is formed from integrating views at limiting points in the environment. Each view affords an adequate description of the spatial layout of a local environment and its limiting point is detected via a process of recognizing significant features in it and tracking them across views. This paper discusses the implementation of this theory on a laser-ranging mobile robot. Two algorithms were implemented to produce two different kinds of maps; one which is sparse and fragmented, and the other which is dense and detailed. Both algorithms successfully generated maps that preserve well the layout of the environment. The implementation provides insights into the problem of loop closing, moving in featureless environments, seeing a stable world, and augmenting mapping with commonsense knowledge.