Alexander Skoglund, Boyko Iliev, Rainer Palm
Programming-by-Demonstration of reaching motions - A next-state-planner approach
Robotics and Autonomous Systems, Volume 58, Issue 5, 11 April 2010, pp. 607-621.
Abstract: This paper presents a novel approach to skill acquisition from human demonstration. A robot manipulator with a morphology which is very different from the human arm simply cannot copy a human motion, but has to execute its own version of the skill. When a skill once has been acquired the robot must also be able to generalize to other similar skills, without a new learning process. By using a motion planner that operates in an object-related world frame called hand-state, we show that this representation simplifies skill reconstruction and preserves the essential parts of the skill.
Keywords: Programming-by-Demonstration, Hand-state, Motion planner, Fuzzy modeling and Correspondence problem.
Download: [DOI 10.1016/j.robot.2009.12.003]
  AUTHOR = {Alexander Skoglund, Boyko Iliev, Rainer Palm},
  TITLE = {Programming-by-Demonstration of reaching motions - A next-state-planner approach},
  JOURNAL = {Robotics and Autonomous Systems},
  YEAR = {2010},
  VOLUME = {58},
  NUMBER = {5},
  PAGES = {607--621},
  MONTH = {April}