A Relational Representation for Procedural Task Knowledge
Abstract
This paper proposes a methodology for learning joint probability estimates regarding the effect of sensorimotor features on the predicated quality of desired behavior. These relationships can then be used to choose actions that will most likely produce success. relational dependency networks are used to learn statistical models of procedural task knowledge. An example task expert for picking up objects is learned through actual experience with a humanoid robot. We believe that this approach is widely applicable and has great potential to allow a robot to autonomously determine which features in the world are salient and should be used to recommend policy for action.
Cite
Text
Hart et al. "A Relational Representation for Procedural Task Knowledge." AAAI Conference on Artificial Intelligence, 2005.Markdown
[Hart et al. "A Relational Representation for Procedural Task Knowledge." AAAI Conference on Artificial Intelligence, 2005.](https://mlanthology.org/aaai/2005/hart2005aaai-relational/)BibTeX
@inproceedings{hart2005aaai-relational,
title = {{A Relational Representation for Procedural Task Knowledge}},
author = {Hart, Stephen and Grupen, Roderic A. and Jensen, David D.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2005},
pages = {1280-1285},
url = {https://mlanthology.org/aaai/2005/hart2005aaai-relational/}
}