Concept Sharing between Human and Interface Agent under Time Criticality

Abstract

In this paper, instead of designing an automation system that is intended to replace a human operator completely with it and to exclude him/her out of the loop, we introduce an idea of an interface agent as a sophisticated associate for a human operator. Since its decision making style must be close to the human's proficient naturalistic decision making, we formalize its resourcebounded reasoning under critical time pressure by joining a machine learning method for concept induction and a classical decision theory.