A Framework for Dynamic Context-Centric Commander Decision Support. (September 2016)

• Record Type: Journal Article
• Authors: Santos, Eugene; Nguyen, Hien; Russell, Jacob; Day, Joshua; Pegleow, Scott; Greenstreet, Alexis
• Is Part Of: Proceedings of the Human Factors and Ergonomics Society ... Annual Meeting. Volume 60:Part 1(2016)
• Page Start: 218
• Page End: 222
• Publication Date: 2016-09
• Subjects: Human engineering -- Congresses; 620.8205
• DOI: 10.1177/1541931213601049
• Languages: English
• ISSNs: 1541-9312

Abstract

This paper addresses the fundamental research question: "How can we determine the sequential decision- making process inside a decision maker's mind?" We construct a dynamic Markov Decision Process using a Double Transition Model (DTM). The DTM is a cognitive model decomposing the decision-making process into episodic tasks that are extracted from a stream of incoming information. In a DTM, each state reflects a stage en route to a decision, and each action reflects a possible move from collecting data to hypothesizing and inferencing. The reward reflects how close a stage is to the final decision. We demonstrate this process through a proof-of-concept DTM using a hypothetical scenario for Typhoon Haiyan in the Philippines (2013). The DTM constructed from this scenario enables a Commander to reason about damaged areas, death tolls, and assistance methods while allowing his actions to be captured and used to explain why and how each decision is made.