Alexander Skoglund, Boyko Iliev and Rainer Palm
A Hand State Approach to Imitation with a Next-State-Planner for Industrial Manipulators
Proceedings of the 2008 International Conference on Cognitive Systems
Abstract: In this paper we present an approach to reproduce human demonstrations in a reach-to-grasp context. The demonstration is represented in hand state space. By using the distance to the target object as a scheduling variable, the way in which the robot approaches the object is controlled. The controller that we deploy to execute the motion is formulated as a nextstate- planner. The planner produces an action from the current state instead of planning the whole trajectory in advance which can be error prone in non-static environments. The results have a direct application in Programming-by-Demonstration. It also contributes to cognitive systems since the ability to reach-tograsp supports the development of cognitive abilities.
Download: [PDF (0.3MB)]
Bibtex:
@INPROCEEDINGS{Skoglund:2008,
  AUTHOR = {Skoglund, Alexander and Iliev, Boyko and Palm, Rainer},
  TITLE = {A Hand State Approach to Imitation with a Next-State-Planner for Industrial Manipulators},
  BOOKTITLE = {Proceedings of the 2008 International Conference on Cognitive Systems},
  PAGES = {130--137},
  YEAR = {2008},
  MONTH = {April 2-4},
  ADRESS = {University of Karlsruhe, Karlsruhe, Germany}
}