One-shot robot programming by demonstration by adapting motion segments
Authors:
- Christian GrothCGChristian Groth
- Dominik HenrichDHDominik Henrich
- 1 December 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1068-1075
Abstract
In order to provide robots for a wide range of users, they must be easily programmable. This is addressed by various approaches of programming a robot by demonstration, where the user guides a robot through the task. We propose an approach that adapts a once demonstrated trajectory to a new situation. The system extracts the relevant reference frames using a weighting function. Then, the demonstrated trajectory is segmented with respect to these frames and different frame-dependent strategies for reproduction are applied. The approach is capable of adapting simple point-to-point paths, more complex tasks like pick-and-place operations, and manipulations where objects are used as tools. Additionally, the system extracts the required resources for a task to integrate the approach into a behavior-based system, which manages new programmed behaviors and selects a suitable behavior in a new situations. The approach is computationally efficient and comprehensible for the user. We evaluated the approach qualitatively and quantitatively using cross validation.Keywords
This publication has 19 references indexed in Scilit:
- A User Study on Kinesthetic Teaching of Redundant Robots in Task and Configuration SpaceJournal of Human-Robot Interaction, 2013
- Active Choice of Teachers, Learning Strategies and Goals for a Socially Guided Intrinsic Motivation LearnerPaladyn, 2012
- A survey of robot learning from demonstrationRobotics and Autonomous Systems, 2009
- Policy Learning for Motor SkillsLecture Notes in Computer Science, 2008
- Interactive robot task training through dialog and demonstration2007
- Towards Cognitive Robots: Building Hierarchical Task Representations of Manipulations from Human Demonstration2006
- Interactive Multimodal Robot ProgrammingThe International Journal of Robotics Research, 2005
- Natural methods for robot task learning2003
- A behavior-based mobile robot architecture for Learning from DemonstrationRobotics and Autonomous Systems, 2001
- Learning Robot Behaviour and Skills Based on Human Demonstration and Advice: The Machine Learning Paradigm2000