Tailoring a cognitive model for situation awareness using machine learning

• Published in: Applied intelligence (Dordrecht, Netherlands) Vol. 42; no. 1; pp. 36 - 48
• Main Authors: Koopmanschap, Richard, Hoogendoorn, Mark, Roessingh, Jan Joris
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.01.2015; Springer Nature B.V
• Subjects: Air combat; Aircraft; Algorithms; Artificial Intelligence; Belief networks; Case studies; Cognition & reasoning; Cognitive models; Computer Science; Decision making; Fighter; Genetic algorithms; Intelligent agents; Knowledge; Machine learning; Machines; Manufacturing; Mechanical Engineering; Memory; Pilots; Processes; Reinforcement; Simulation; Subject specialists; Situation awareness; Cognitive model; Simulation; Neural networks; Evolutionary algorithm; Machine learning
• ISSN: 0924-669X; 1573-7497
• DOI: 10.1007/s10489-014-0584-3

Using a pure machine learning approach to enable the generation of behavior for agents in serious gaming applications can be problematic, because such applications often require human-like behavior for agents that interact with human players. Such human-like behavior is not guaranteed with e.g. basic reinforcement learning schemes. Cognitive models can be very useful to establish human-like behavior in an agent. However, they require ample domain knowledge that might be difficult to obtain. In this paper, a cognitive model is taken as a basis, and the addition of scenario specific information is for a large part automated by means of machine learning techniques. The performance of the approach of automatically adding scenario specific information is rigorously evaluated using a case study in the domain of fighter air combat. An evolutionary algorithm is proposed for automatically tailoring a cognitive model for situation awareness of fighter pilots. The standard algorithm and several extensions are evaluated with respect to performance in air combat. The results show that it is possible to apply the algorithm to optimize belief networks for cognitive models of intelligent agents (adversarial fighters) in the aforementioned domain, thereby reducing the effort required to elicit knowledge from experts, while retaining the required ‘human-like’ behavior.