Ontologies for reasoning about failures in AI systems (2007)
| Venue: | in Proceedings from the Workshop on Metareasoning in Agent Based Systems at the Sixth International Joint Conference on Autonomous Agents and Multiagent Sytems |
| Citations: | 6 - 5 self |
BibTeX
@INPROCEEDINGS{Schmill07ontologiesfor,
author = {Matthew D. Schmill and Darsana Josyula and Michael L. Anderson and Shomir Wilson and Tim Oates and Don Perlis and Dean Wright and Scott Fults},
title = {Ontologies for reasoning about failures in AI systems},
booktitle = {in Proceedings from the Workshop on Metareasoning in Agent Based Systems at the Sixth International Joint Conference on Autonomous Agents and Multiagent Sytems},
year = {2007}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Abstract. Brittleness is a common problem among AI systems. Autonomous systems, including those that learn, may be faced with unanticipated situations that cause decreased performance, or in the worstcase, catastrophic failures from which the system cannot recover. In this paper, we describe a construct called the metacognitive loop (MCL) that allows AI systems to monitor their own behavior, generate expectations about their own progress and performance, and verify that they are met. When expectations are violated, the metacognitive loop attempts to reason in a domain-general way about why expectations were not met and how to recover. The basis for reasoning is a set of ontologies that encode abstract diagnosic and prescriptive processes for coping with failures. 1
