Autonomous Development of a Grounded Object Ontology by a Learning Robot
Abstract
We describe how a physical robot can learn about objects from its own autonomous experience in the continuous world. The robot identifies statistical regularities that allow it to represent a physical object with a cluster of sensations that violate a static world model, track that cluster over time, extract percepts from that cluster, form concepts from similar percepts, and learn reliable actions that can be applied to objects. We present a formalism for representing the ontology for objects and actions, a learning algorithm, and the results of an evaluation with a physical robot.
Cite
Text
Modayil and Kuipers. "Autonomous Development of a Grounded Object Ontology by a Learning Robot." AAAI Conference on Artificial Intelligence, 2007.Markdown
[Modayil and Kuipers. "Autonomous Development of a Grounded Object Ontology by a Learning Robot." AAAI Conference on Artificial Intelligence, 2007.](https://mlanthology.org/aaai/2007/modayil2007aaai-autonomous/)BibTeX
@inproceedings{modayil2007aaai-autonomous,
title = {{Autonomous Development of a Grounded Object Ontology by a Learning Robot}},
author = {Modayil, Joseph and Kuipers, Benjamin},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2007},
pages = {1095-1101},
url = {https://mlanthology.org/aaai/2007/modayil2007aaai-autonomous/}
}