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.
| Author(s): | Kroemer, O. and Detry, R. and Piater, J. and Peters, J. |
| Links: | |
| Journal: | IROS 2010 Workshop on Grasp Planning and Task Learning by Imitation |
| Volume: | 2010 |
| Pages: | 1 |
| Year: | 2010 |
| Month: | October |
| Day: | 0 |
| BibTeX Type: | Poster (poster) |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
BibTeX
@poster{6852,
title = {Generalizing Demonstrated Actions in Manipulation Tasks},
journal = {IROS 2010 Workshop on Grasp Planning and Task Learning by Imitation},
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.},
volume = {2010},
pages = {1},
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
month = oct,
year = {2010},
author = {Kroemer, O. and Detry, R. and Piater, J. and Peters, J.},
month_numeric = {10}
}