Human–agent teamwork in dynamic environments

Confronting barriers to human-robot cooperation: balancing efficiency and risk in machine behavior

Many technical and psychological challenges make it difficult to design machines that effectively cooperate with people. To better understand these challenges, we conducted a series of studies investigating human-human, robot-robot, and human-robot cooperation in a strategically rich resource-sharing scenario, which required players to balance efficiency, fairness, and risk. In these studies, both human-human and robot-robot dyads typically learned efficient and risky cooperative solutions when they could communicate. In the absence of communication, robot dyads still often learned the same efficient solution, but human dyads achieved a less efficient (less risky) form of cooperation. This difference in how people and machines treat risk appeared to discourage human-robot cooperation, as human-robot dyads frequently failed to cooperate without communication. These results indicate that machine behavior should better align with human behavior, promoting efficiency while simultaneously considering human tendencies toward risk and fairness.

•

Experiments show that people learned risk-averse solutions without communication

•

With and without communication, robot pairs learned risky, but efficient, outcomes

•

Human-robot pairs often learned risky, but efficient, solutions with communication

•

Without communication, behavioral asymmetries inhibited human-robot cooperation

The Impact of Multimodal Communication on a Shared Mental Model, Trust, and Commitment in Human–Intelligent Virtual Agent Teams

There is an increasing interest in the use of intelligent virtual agents (IVAs) to work in teams with humans. To achieve successful outcomes for these heterogeneous teams, many of the aspects found in successful human teams will need to be supported. These aspects include behavioural (i.e., multimodal communication), cognitive (i.e., a shared mental model (SMM)), and social (trust and commitment). Novelly, this paper aims to investigate the impact of IVA’s multimodal communication on the development of a SMM between humans and IVAs. Moreover, this paper aims to explore the impact of the developed SMM on a human’s trust in an IVA’s decisions and a human’s commitment to honour his/her promises to an IVA. The results from two studies involving a collaborative activity showed a significant positive correlation between team multimodal communication (i.e., behavioural aspect) and a SMM between teammates (i.e., cognitive aspect). Moreover, the result showed that there is a significant positive correlation between the developed SMM and a human’s trust in the IVA’s decision and the human’s commitment to honour his/her promises (the establishment of the social aspect of teamwork). Additionally, the results showed a cumulative effect of all of these aspects on human–agent team performance. These results can guide the design of human–agent teamwork multimodal communication models.