Shape description of general 3D object using tactile sensing information
2004 (English)In: Advances in Modelling and Analysis B, ISSN 1240-4543, Vol. 47, no 5-6, 81-90 p.Article in journal (Refereed) Published
In this paper we consider the problem of recognizing the shape of a 3D object using tactile sensing by a dexterous robot hand. Our approach uses multiple fingers to slide along the surface of the object. From the sensing contact points we extracts a number of 3D points belonging to the surface of the object. The unknown surface Γ of the object is determined by using an "n-ellipsoid" model (Bonnet ). The set of parameters that define the surface Γ is determined such that the nellipsoid best fits the set of data points, by using a genetic algorithm.
Place, publisher, year, edition, pages
2004. Vol. 47, no 5-6, 81-90 p.
Dexterous robot hand, Genetic algorithm, Global volumetric deformation technique (FFD), N-ellipsoid, Unknown geometry, Approximation theory, Data processing, Genetic algorithms, Mathematical models, Microsensors, Pattern recognition, Dextrous robot hand, N-ellipsoids, Robotic arms
Computer and Information Science
IdentifiersURN: urn:nbn:se:kth:diva-157266ScopusID: 2-s2.0-18444409384OAI: oai:DiVA.org:kth-157266DiVA: diva2:771294
QC 201412122014-12-122014-12-082014-12-12Bibliographically approved