Making Virtual Pancakes — Acquiring and Analyzing Data of Everyday Manipulation Tasks through Interactive Physics-based Simulations
BibTeX
@MISC{Kunze_makingvirtual,
author = {Lars Kunze and Andrei Haidu and Michael Beetz},
title = {Making Virtual Pancakes — Acquiring and Analyzing Data of Everyday Manipulation Tasks through Interactive Physics-based Simulations},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Teaching robots everyday tasks like making pancakes by instructions requires interfaces that can be intuitively operated by nonexperts. By performing manipulation tasks in a virtual environment using a data glove task-related information of the demonstrated actions can directly be accessed and extracted from the simulator. We translate low-level data structures of these simulations into meaningful first-order representations, called timelines, whereby we are able to select data segments and analyze them at an abstract level. Hence, the proposed system is a powerful tool for acquiring examples of manipulation actions and for analyzing them whereby robots can be informed how to perform a task. 1
Keyphrases
everyday manipulation task virtual pancake acquiring analyzing data interactive physics-based simulation demonstrated action robot everyday task low-level data structure meaningful first-order representation data glove task-related information abstract level virtual environment manipulation task powerful tool manipulation action data segment
