Human-agent Teams Research Articles

Learning HMM-based cognitive load models for supporting human-agent teamwork

Cognitive studies indicate that members of a high performing team often develop shared mental models to predict others’ needs and coordinate their behaviors. The concept of shared mental models is especially useful in the study of human-centered collaborative systems that require humans to team with autonomous agents in complex activities. We take the position that in a mixed human-agent team, agents empowered with cognitive load models of human team members can help humans develop better shared mental models to enhance team performance. Inspired by human information processing system, we here propose a HMM-based load model for members of human-agent teams, and investigate the development of realistic cognitive load models. A cognitive experiment was conducted in team contexts to collect data about the observable secondary task performance of human participants. The data were used to train hidden Markov models (HMM) with varied numbers of hypothetical hidden states. The result indicates that the model spaces have a three-layer structure. Statistical analysis also reveals some characteristics of the models at the top-layer. This study can be used in guiding the selection of HMM-based cognitive load models for agents in human-centered multi-agent systems.

Using Simulation to investigate a Non-Anthropomorphic Framework for Communications within a Human-Agent War-Fighting Team

As complex, non-human agents become increasingly ubiquitous members of the US military war-fighting team, an effective and natural system of communications must be explored and developed to achieve human-agent collaboration across the entire team. A non-anthropomorphic communications framework does not exist that will support human-agent collaboration beyond current electronic control. This research surfaces a non-anthropomorphic framework of communications between human-human, human-agent, and agent-agent teams based on related literature review. The framework provides perspective on the potential breath of communication modalities that exist as well as the many challenges faced. Within this framework, this research uses simulation to explore the contribution to collaborative, covert military operations that non-verbal forms of communications between humans and agent team members might entail. Visual and audio cues considered include pose, motion, color, and non-speech sounds. In addition this article presents findings on contribution of these modalities to the military operation being considered as well as identifies issues for implementation, applications, implications, and areas for future research.

Developing an Interdisciplinary Language for Human-Agent Team Training Research

In this paper we explore a set of constructs across three diverse disciplines that have addressed the topic of intelligent agents. We explore how Computer Science, Psychology, and Philosophy discuss certain concepts in either convergent or divergent ways. These concepts are analyzed through their etymology as well as by their present usage to illustrate how this use has developed and to outline the similarities and differences that have emerged. We first describe a set of the concepts/terms found within this literature and then describe the implications of this analysis for research in human-agent teams.

Towards flexible coordination of human-agent teams

Enabling interactions of agent-teams and humans is a critical area of research, with encouraging progress in the past few years. However, previous work suffers from three key limitations: (i) limited human situational awareness, reducing human effect