Alexander Skoglund and Boyko Iliev and Bourhane Kadmiry and Rainer Palm
Programming by Demonstration of Pick-and-Place Tasks for Industrial Manipulators using Task Primitives
IEEE Int. Symposium on Computational Intelligence in Robotics and Automation 2007, pp. 368-373
Abstract: This article presents an approach to Programming by Demonstration (PbD) to simplify programming of industrial manipulators. By using a set of task primitives for a known task type, the demonstration is interpreted and a manipulator program is automatically generated. A pick-and-place task is analyzed, based on the velocity profile, and decomposed in task primitives. Task primitives are basic actions of the robot/gripper, which can be executed in a sequence to form a complete a task. For modeling and generation of the demonstrated trajectory, fuzzy time clustering is used, resulting in smooth and accurate motions. To illustrate our approach, we carried out our experiments on a real industrial manipulator.
Download: [PDF (0.7MB)]
Bibtex:
@INPROCEEDINGS{Skoglund:2007,
  AUTHOR = {Alexander Skoglund and Boyko Iliev and Bourhane Kadmiry and Rainer Palm},
  TITLE = {Programming by Demonstration of Pick-and-Place Tasks for Industrial Manipulators using Task Primitives},
  BOOKTITLE = {{IEEE} International Symposium on Computational Intelligence in Robotics and Automation},
  PAGES = {368--373},
  YEAR = {2007},
  MONTH = {June 20-23},
  DOI = {10.1109/CIRA.2007.382863}
}