English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Meeting Abstract

Generalizing Demonstrated Actions in Manipulation Tasks

MPS-Authors
/persons/resource/persons84027

Kroemer,  O
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons227658

Detry,  R
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84139

Piater,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons84135

Peters,  J
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

External Resource
Fulltext (public)

Kroemer-IROS-GraspWorkshop.pdf
(Any fulltext), 6MB

Supplementary Material (public)
There is no public supplementary material available
Citation

Kroemer, O., Detry, R., Piater, J., & Peters, J. (2010). Generalizing Demonstrated Actions in Manipulation Tasks. In IROS 2010 Workshop on Grasp Planning and Task Learning by Imitation.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-BDF8-0
Abstract
Programming-by-demonstration promises to significantly reduce the burden of coding robots to perform new tasks. However, service robots will be presented with a variety of different situations that were not specifically demonstrated to it. In such cases, the robot must autonomously generalize its learned motions to these new situations. We propose a system that can generalize movements to new target locations and even new objects. The former is achieved by using a task-specific coordinate system together with dynamical systems motor primitives. Generalizing actions to new objects is a more complex problem, which we solve by treating it as a continuum-armed bandits problem. Using the bandits framework, we can efficiently optimize the learned action for a specific object. The proposed method was implemented on a real robot and succesfully adapted the grasping action to three different objects. Although we focus on grasping as an example of a task, the proposed methods are much more widely applicable to robot manipulation tasks.