Active Ambiguity Reduction: An Experiment Design Approach to Tractable Qualitative Reasoning

摘要

Ambiguity is a limiting obstacle to qualitative reasoning systems. In this paper, we present a new approach called active ambiguity reduction to deal with this problem. Active ambiguity reduction involves the purposeful alteration of the world to generate new information. Ths new information will be inconsistent with some of the ambiguous situations, thereby eliminating them from further consideration. Active ambiguity reduction may also be viewed as experiment design. This paper presents a theory of experiment design which is based on the principle of refutation. The theory describes three strategies for designing experiments - elaboration, discrimination and transformation. the theory and an experiment engine - an implementation of the theory - are illustrated using a detailed example which uses qualitative reasoning task like determining activity, envisionment and measurement interpretation. Importantly, the experiment engine is general and domain-independent and therefore readily integrable with existing qualitative reasoning systems.