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.

PDF, HTML

In Proceedings of the Twenty-Second National Conference on Artificial Intelligence (AAAI-07) 2007.

@inproceedings{modayil:aaai07, title={Autonomous Development of a Grounded Object Ontology by a Learning Robot}, author={Joseph Modayil and Benjamin Kuipers}, booktitle={Proceedings of the Twenty-Second National Conference on Artificial Intelligence (AAAI-07)}, url="http://www.cs.utexas.edu/users/ai-lab?modayil:aaai07", year={2007} }