Maintaining consistency in hierarchical reasoning

• Authors: Robert E. Wray, III;John Laird
• Venue: AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
• Year: 1998

We explore techniques for maintaining consistency in reasoning when employing dynamic hierarchical task decompositions. In particular, we consider the difficulty of maintaining consistency when an agent nonmonotonically modifies an assumption in one level of the task hierarchy and that assumption depends upon potentially dynamic assertions higher in the hierarchy. The hypothesis of our work is that reasoning maintenance can be extended to hierarchical systems such that consistency is maintained across all levels of the hierarchy. We introduce two novel extensions to standard reason maintenance approaches, assumption justification and dynamic hierarchical justification, both of which provide the necessary capabilities. The key difference between the two methods is whether a particular assumption (assumption justification) or an entire level of the hierarchy (dynamic hierarchical justification) is disabled when an inconsistency is found. Our investigations suggest that dynamic hierarchical justification has advantages over assumption justification, especially when the task decomposition is wellconstructed. Agents using dynamic hierarchical justification also compare favorably to agents using less complete methods for reasoning consistency, improving the reactivity of hierarchical architectures while eliminating the need for knowledge that otherwise would be required to maintain reasoning consistency.