Human Digital Twin—Enabling Human-Agents Collaboration

Abstract

Smart environments, such as Industry 4.0 or smart cities, are based on digital technologies that collect large amounts of data and artificial intelligence applications—or agents—to analyze this data and optimize various operational aspects of the environment. However, any intelligent environment must include humans. In this case, the interactions between humans and agents, referred to as human-agent interaction (HAI), will occur in complex arrangements involving multiple humans and agents interacting concurrently along with various scenarios. Agents’ ability to learn and perform their tasks is contingent on some degree of consistency in their interactions with humans. A lack of such consistency would jeopardize their learning and performance. It is thus necessary to integrate humans and agents across the entire environment consistently. Assuming that HAI is a complex system, the paper argues that ensuring HAI consistency can be achieved by deploying a new class of agents devoted to managing human-agent interactions, the Human Digital Twin (HDT). The proposed HDTs are placed alongside each human in the HAI environment to observe and learn about their interaction patterns and then use them to ensure HAI consistency.