Becoming Team Members: Identifying Interaction Patterns of Mutual Adaptation for Human-Robot Co-Learning.

Emma M Van Zoelen,Mark Neerincx,Karel Van Den Bosch

doi:10.3389/frobt.2021.692811

Abstract

Becoming a well-functioning team requires continuous collaborative learning by all team members. This is called co-learning, conceptualized in this paper as comprising two alternating iterative stages: partners adapting their behavior to the task and to each other (co-adaptation), and partners sustaining successful behavior through communication. This paper focuses on the first stage in human-robot teams, aiming at a method for the identification of recurring behaviors that indicate co-learning. Studying this requires a task context that allows for behavioral adaptation to emerge from the interactions between human and robot. We address the requirements for conducting research into co-adaptation by a human-robot team, and designed a simplified computer simulation of an urban search and rescue task accordingly. A human participant and a virtual robot were instructed to discover how to collaboratively free victims from the rubbles of an earthquake. The virtual robot was designed to be able to real-time learn which actions best contributed to good team performance. The interactions between human participants and robots were recorded. The observations revealed patterns of interaction used by human and robot in order to adapt their behavior to the task and to one another. Results therefore show that our task environment enables us to study co-learning, and suggest that more participant adaptation improved robot learning and thus team level learning. The identified interaction patterns can emerge in similar task contexts, forming a first description and analysis method for co-learning. Moreover, the identification of interaction patterns support awareness among team members, providing the foundation for human-robot communication about the co-adaptation (i.e., the second stage of co-learning). Future research will focus on these human-robot communication processes for co-learning.

Highlights

When people collaborate in teams, it is of key importance that all team members get to know each other, explore how they can best work together, and eventually adapt to each other and learn to make their collaboration as fluent as possible
From the analysis of the observed human-robot interactions, a list of patterns of adaptive interactions, and the switching between these patterns over time, were identified. These patterns can emerge in similar task contexts, forming a first description method for co-learning analyses
Following from this, and to provide a broader view on the specific study that we present in this paper, we have defined three research directions that need to be addressed in the study of human-robot co-learning: 1. Research into enabling and assessing co-learning: to understand the dynamics of co-learning, we need to investigate what kind of behaviors and interactions drive co-adaptation and co-learning, and how learning processes of human and robot team members influence each other

Summary

Introduction

When people collaborate in teams, it is of key importance that all team members get to know each other, explore how they can best work together, and eventually adapt to each other and learn to make their collaboration as fluent as possible. While humans do this naturally (Burke et al, 2006), it is not self-evident for robots that are intended to function as team partners in human-robot collaborations. Partners observe each other and adapt their behavior to the other, leading to successful emergent team behaviors Such adaptation can be done deliberately but often occurs implicitly and unconsciously. This second stage of creating awareness of what has been learned helps to sustain the behavioral adaptations over time and across contexts

Results

Discussion

Conclusion