Abstract
The rapid progress in artificial intelligence enables technology to more and more become a partner of humans in a team, rather than being a tool. Even more than in human teams, partners of human–agent teams have different strengths and weaknesses, and they must acknowledge and utilize their respective capabilities. Coordinated team collaboration can be accomplished by smartly designing the interactions within human–agent teams. Such designs are called Team Design Patterns (TDPs). We investigated the effects of a specific TDP on proactive task reassignment. This TDP supports team members to dynamically allocate tasks by utilizing their knowledge about the task demands and about the capabilities of team members. In a pilot study, agent–agent teams were used to study the effectiveness of proactive task reassignment. Results showed that this TDP improves a team’s performance, provided that partners have accurate knowledge representations of each member’s skill level. The main study of this paper addresses the effects of task reassignments in a human–agent team. It was hypothesized that when agents provide explanations when issuing and responding to task reassignment requests, this will enhance the quality of the human’s mental model. Results confirmed that participants developed more accurate mental models when agent-partners provide explanations. This did not result in a higher performance of the human–agent team, however. The study contributes to our understanding of designing effective collaboration in human–agent teams.
Highlights
The increasing development of Artificial Intelligence (AI) and technological innovations are changing the way individuals and teams learn and perform their tasks
Testing the effectiveness of the Team Design Patterns (TDPs) is important, as in the main study (Section 5) we investigate whether adding the element of “providing explanations” to the TDP leads to a better understanding in the human agent, and whether it yields additional effects on the team’s functioning and performance
In order to investigate whether people managed to develop accurate mental models of their robot team members, we analyze their ability to choose the best agent for a specific task, to choose the best task for a specific agent, and to predict the task request/response behavior of both agent team members in specific scenarios
Summary
Before an agent proceeds to the compartment of its route, it first checks whether it has received a request to take over a task of another team member. It starts the procedure to consider whether to accept or to decline the request (see below) If not, it proceeds with its own assigned task. The machine agent in the presented experiments has a strictly-defined knowledge representation It holds for each agent an estimation of their skill levels for each type of skill. During the execution of the task, skill levels may be adapted based on interactions, for example a team member that refuses work. This knowledge representation works well when interacting with other robot agents, as these work with the same paradigm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
