Movement Coordination in Human-Robot Teams: A Dynamical Systems Approach

TL;DR

This paper presents a dynamical systems approach enabling robots to perceive, anticipate, and synchronize with human group motion in real-time, improving coordination in joint human-robot activities such as dancing.

Contribution

The paper introduces a novel anticipation method that incorporates high-level group behavior to enhance robot-human motion synchronization in real-time scenarios.

Findings

The proposed method achieves better synchronization with human groups.

Robots exhibit more contingent and fluent motion when understanding group behavior.

The approach outperforms methods lacking high-level behavior modeling.

Abstract

In order to be effective teammates, robots need to be able to understand high-level human behavior to recognize, anticipate, and adapt to human motion. We have designed a new approach to enable robots to perceive human group motion in real-time, anticipate future actions, and synthesize their own motion accordingly. We explore this within the context of joint action, where humans and robots move together synchronously. In this paper, we present an anticipation method which takes high-level group behavior into account. We validate the method within a human-robot interaction scenario, where an autonomous mobile robot observes a team of human dancers, and then successfully and contingently coordinates its movements to "join the dance". We compared the results of our anticipation method to move the robot with another method which did not rely on high-level group behavior, and found our method performed better both in terms of more closely synchronizing the robot's motion to the team, and also exhibiting more contingent and fluent motion. These findings suggest that the robot performs better when it has an understanding of high-level group behavior than when it does not. This work will help enable others in the robotics community to build more fluent and adaptable robots in the future.