Multi-fingered robot grasping is a challenging problem that is difficult to tackle using hand-coded programs. In this paper we present an imitation learning approach for learning and generalizing grasping skills based on human demonstrations. To this end, we split the task of synthesizing a grasping motion into three parts: (1) learning efficient grasp representations from human demonstrations, (2) warping contact points onto new objects, and (3) optimizing and executing the reach-and-grasp movements. We learn low-dimensional latent grasp spaces for different grasp types, which form the basis for a novel extension to dynamic motor primitives. These latent-space dynamic motor primitives are used to synthesize entire reach-and-grasp movements. We evaluated our method on a real humanoid robot. The results of the experiment demonstrate the robustness and versatility of our approach.


    Access

    Download


    Export, share and cite



    Title :

    Generalization of human grasping for multi-fingered robot hands


    Contributors:

    Conference:


    Publication date :

    2012


    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    DLR Multi-fingered Hands

    Grebenstein, Markus / Chalon, Maxime / Roa, Máximo A. et al. | Springer Verlag | 2018


    Optimum grasping planning for multi-fingered dextrous hands based on the asymptotical stability

    Yang, Y. / Lu, Z. / Zhang, Q. | British Library Online Contents | 1996


    Structural Synthesis of Multi-Fingered Hands

    Lee, Jyh-Jone | Online Contents | 2002



    Seamless Manipulation by Multi-fingered Robot Hands Based on Global Expression of System Motion

    Nagase, K. / Kikuchi, N. | British Library Online Contents | 2014