• DocumentCode
    565592
  • Title

    Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective

  • Author

    Akgun, Baris ; Cakmak, Maya ; Yoo, Jae Wook ; Thomaz, Andrea L.

  • Author_Institution
    Sch. of Interactive Comput., Georgia Inst. of Technol., Atlanta, GA, USA
  • fYear
    2012
  • fDate
    5-8 March 2012
  • Firstpage
    391
  • Lastpage
    398
  • Abstract
    Kinesthetic teaching is an approach to providing demonstrations to a robot in Learning from Demonstration whereby a human physically guides a robot to perform a skill. In the common usage of kinesthetic teaching, the robot´s trajectory during a demonstration is recorded from start to end. In this paper we consider an alternative, keyframe demonstrations, in which the human provides a sparse set of consecutive keyframes that can be connected to perform the skill. We present a user-study (n = 34) comparing the two approaches and highlighting their complementary nature. The study also tests and shows the potential benefits of iterative and adaptive versions of keyframe demonstrations. Finally, we introduce a hybrid method that combines trajectories and keyframes in a single demonstration.
  • Keywords
    human-robot interaction; learning (artificial intelligence); robot programming; student experiments; trajectory control; human-robot interaction; keyframe demonstrations; kinesthetic teaching; learning-from-demonstration; robot skill programming; robot trajectory; Education; Humans; Joints; Robots; Speech; Trajectory; USA Councils; Learning from Demonstration;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Human-Robot Interaction (HRI), 2012 7th ACM/IEEE International Conference on
  • Conference_Location
    Boston, MA
  • ISSN
    2167-2121
  • Print_ISBN
    978-1-4503-1063-5
  • Electronic_ISBN
    2167-2121
  • Type

    conf

  • Filename
    6249584