• DocumentCode
    2007918
  • Title

    Towards Associative Skill Memories

  • Author

    Pastor, Peter ; Kalakrishnan, Mrinal ; Righetti, Ludovic ; Schaal, Stefan

  • Author_Institution
    Comput. Learning & Motor Control Lab., Univ. of Southern California, Los Angeles, CA, USA
  • fYear
    2012
  • fDate
    Nov. 29 2012-Dec. 1 2012
  • Firstpage
    309
  • Lastpage
    315
  • Abstract
    Movement primitives as basis of movement planning and control have become a popular topic in recent years. The key idea of movement primitives is that a rather small set of stereotypical movements should suffice to create a large set of complex manipulation skills. An interesting side effect of stereotypical movement is that it also creates stereotypical sensory events, e.g., in terms of kinesthetic variables, haptic variables, or, if processed appropriately, visual variables. Thus, a movement primitive executed towards a particular object in the environment will associate a large number of sensory variables that are typical for this manipulation skill. These association can be used to increase robustness towards perturbations, and they also allow failure detection and switching towards other behaviors. We call such movement primitives augmented with sensory associations Associative Skill Memories (ASM). This paper addresses how ASMs can be acquired by imitation learning and how they can create robust manipulation skill by determining subsequent ASMs online to achieve a particular manipulation goal. Evaluation for grasping and manipulation with a Barrett WAM/Hand illustrate our approach.
  • Keywords
    dexterous manipulators; learning (artificial intelligence); motion control; path planning; ASM; Barrett WAM/Hand; associative skill memories; complex manipulation skills; failure detection; grasping; haptic variables; imitation learning; kinesthetic variables; movement control; movement planning; movement primitives; robust manipulation skill; sensory associations; stereotypical movements; stereotypical sensory events; visual variables; Fingers; Force; Robot sensing systems; Torque; Trajectory; Uncertainty;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Humanoid Robots (Humanoids), 2012 12th IEEE-RAS International Conference on
  • Conference_Location
    Osaka
  • ISSN
    2164-0572
  • Type

    conf

  • DOI
    10.1109/HUMANOIDS.2012.6651537
  • Filename
    6651537