On Modeling and Simulating Agent Teamwork in Cast

Abstract

Effective human teams use overlapping shared mental models for anticipating information needs of teammates and for offering relevant information proactively. The long-term goal of our research is to empower agents with such "shared mental models" so that they can be used to better simulate, train, or support human teams for their information fusion, interpretation, and decisions. Toward this goal, we have developed a team agent architecture called CAST that enables agents to infer information needs of teammates, which further enables agents to assist teammates by proactively delivering needed information to them. In this paper, we focus on two key issues related to proactive information delivery behavior. First, we model the semantics of proactive information delivery as an attempt (called ProAssert), which extends the performative Assert in Joint Intention Theory. Second, we introduce a decision-theoretic approach for reasoning about whether to act on a potential proactive assert. Experimental results suggested that the decision-theoretic communication strategy enhances the team performance. The formal semantics and the decision-theoretic communication strategies together provide a sound and practical framework that enables further studies regarding proactive information delivery for supporting the decision making of a team involving human and agents.

Agent Based Intelligent System for Enhanced Teamwork Performance

“…Although there has been little study on multi-agent systems as a potential option for team training, we will first quickly review the ideas that have been produced as the basis for collaboration in this part. and then examine the main agent-based collaboration designs that facilitate team member coordination and communication [5][6][7]. In order to capture the essential elements of collaboration and system modeling of team behavior, a number of theoretical frameworks were put forth under the Belief-Desire-Intention (BDI) agency paradigm.…”

Imitating human responses via a Dual-Process Model

“…SMMs are a paramount factor for the success of cooperative work (Hanna, et al, 2018). An abundant amount of existing research explores SMMs, but the research mainly focused on teams only comprised of humans (Grim, et al, 2016;Tarola, et al, 2018;Wang, et al, 2009;Yen, et al, 2003).With the increase in the number of and complexity of computer agents interacting with human teams, an increased focus has risen in having the computer agent build a shared mental model to strengthen teamwork. The computer agent must somehow algorithmically formalize the SMM.…”