Team Design Patterns for Participatory Development of First Response Human-Agent Teaming

Abstract

First responders (FRs) work in complex and dangerous environments in which information is often uncertain and incomplete. Advancements in artificial intelligence technology pose great potential for supporting FRs throughout dynamic mission developments. We investigated how teamwork between FRs and an intelligent agent should be designed to facilitate adequate decision-making. For this purpose, three Team Design Patterns (TDPs) were created, each assigning different roles and responsibilities to the intelligent agents and FRs. The collaboration was evaluated by presenting two scenarios to FRs in which they had to handle an incident in simulated collaboration with the agents. The results show that preference and acceptance varied across FRs and different decisions and point towards recommending a design solution in which the intelligent agent can adapt its collaboration style to different FRs and decisions it is assisting with.