Model of communication and coordination in a capture-the-flag paradigm

In the modern world the influence of artificial intelligence (AI) is quite large and nowadays there are many attempts of AI integration across domains. In this context, of interest are cognitive architectures that offer the ability to integrate other models including themselves. The purpose of this work is to develop and test a model of management of a team of intelligent agents – actors, based on a system of incentives and goals. To test the idea, we use the agent management mechanism as well as the ability of a cognitive system to adapt to coordination of a group of people. We study not only the overall performance of the concept and its effectiveness in comparison with analogues, but also the prospects of using it over time to manage people in real world situations. It is expected that the usage of this system to coordinate a team of people will increase the team efficiency compared to their own coordination. The paradigm used in this study is a capture-the-flag game with a messaging system built into it. For testing the model, group matches were organized among participants. The collected data was sufficient to prove the concept. The study showed that the implemented coordinator prototype is potentially capable of improving performance of a group of people in the selected paradigm. This article describes the principles underlying the system and methods used for their implementation. Preliminary results suggest that the approach is promising and should be further investigated.