The field of human-robot interaction (HRI) is rapidly expanding, with new developments in technology leading to an increasing number of complex systems that involve multiple robots and/or humans. These multi-agent systems have the potential to greatly enhance the capabilities of robots and the efficiency of human-robot collaboration, but they also introduce new challenges in terms of system design, control, and evaluation. This article presents a survey of literature in the area of Human-Robot Interaction (HRI), specifically on systems containing more than two agents (i.e., having multiple humans and/or multiple robots).

Methods

We began by conducting a systematic literature review, searching for papers that discussed multi-agent HRI systems. These systems were defined as involving multiple robots and/or multiple humans, and could include both cooperative and competitive scenarios. We focused on papers published between 2015 and 2020, in order to capture the most recent developments in the field.

We then analyzed the papers we found, looking for commonalities and differences in terms of system characteristics, such as the number and type of agents involved, the tasks they performed, and the methods used to control and evaluate the systems. We also looked for trends in the literature, such as the most popular application domains and the most frequently used evaluation metrics.

Results

Our literature review identified a total of papers that fit our criteria. The three core aspects of ``Multi-agent" HRI systems that are useful for understanding how these systems differ from dyadic systems and from one another are the Team structure, Interaction style among agents, and the system's Computational characteristics.

Under these core aspects, we present five attributes of HRI systems, namely Team size, Team composition, Interaction model, Communication modalities, and Robot control. These attributes are used to characterize and distinguish one system from another. We populate resulting categories with examples from the recent literature along with a brief discussion of their applications. We also analyze how these attributes in multi-agent systems differ from the case of dyadic human-robot systems.

Conclusions

Through this survey, we summarize key observations from the current literature, and identify challenges and promising areas for future research in this domain. In order to realize the vision of robots being part of the society and interacting seamlessly with humans, there is a need to expand research on multi-human -- multi-robot systems. Not only do these systems require coordination among several agents, they also involve multi-agent and indirect interactions which are absent from dyadic HRI systems. Adding multiple agents in HRI systems requires more advanced interaction schemes, behavior understanding and control methods to allow natural interactions among humans and robots.

In addition, research on human behavioral understanding in mixed human-robot teams also requires more attention. This will help formulate and implement effective robot control policies in HRI systems with large numbers of heterogeneous robots and humans; a team composition reflecting many real-world scenarios.

Read the full paper: "Surveying and classifying multi-agent human-robot systems"

References

1. Abhinav Dahiya, Alexander M. Aroyo, Kerstin Dautenhahn, Stephen L. Smith. "A survey of multi-agent Human–Robot Interaction systems." Robotics and Autonomous Systems, 2022.