The kinematics of a robot with many degrees of freedom is a very complex function. Learning this function for a large workspace with a good precision requires a huge number of training samples, i.e., robot movements. In this paper, we introduce the Kinematic Bézier Map (KB-Map), a parameterizable model without the generality of other systems but whose structure readily incorporates some of the geometric constraints of a kinematic function. In this way, the number of training samples required is drastically reduced. Moreover, the simplicity of the model reduces learning to solving a linear least squares problem. Systematic experiments have been carried out showing the excellent interpolation and extrapolation capabilities of KB-Maps and their relatively low sensitivity to noise. ; Preprint


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Kinematic Bézier maps

    Ulbrich, Stefan / Ruiz de Angulo, Vicente / Torras, Carme et al. | BASE | 2012

    Freier Zugriff

    Rapid learning of humanoid body schemas with kinematic Bezier maps

    Ulbrich, Stefan / Ruiz de Angulo, Vicente / Asfour, Tamim et al. | BASE | 2009

    Freier Zugriff

    Bézier Description of Space Trajectories

    de Dilectis, Francesco / Mortari, Daniele / Zanetti, Renato | AIAA | 2016


    A dynamic Bezier curve model

    Sohel, F.A. / Dooley, L.S. / Karmakar, G.C. | IEEE | 2005


    Geometric Construction of Bezier Motions

    Ge, Q.J. | Online Contents | 1994