Applying the Wizard-of-Oz Technique to Multimodal Human-Robot Dialogue

TL;DR

This paper explores using the Wizard-of-Oz technique with two wizards to simulate multimodal human-robot dialogue, aiding in designing more natural interaction methods for soldiers and robots in exploration tasks.

Contribution

It demonstrates a novel approach of dividing wizard roles for better simulation of robot navigation and dialogue management in collaborative exploration.

Findings

Division of wizard roles is workable for simulating robot behaviors.

The approach shows promise for future software development.

Enhances natural interaction between humans and robots in exploration tasks.

Abstract

Our overall program objective is to provide more natural ways for soldiers to interact and communicate with robots, much like how soldiers communicate with other soldiers today. We describe how the Wizard-of-Oz (WOz) method can be applied to multimodal human-robot dialogue in a collaborative exploration task. While the WOz method can help design robot behaviors, traditional approaches place the burden of decisions on a single wizard. In this work, we consider two wizards to stand in for robot navigation and dialogue management software components. The scenario used to elicit data is one in which a human-robot team is tasked with exploring an unknown environment: a human gives verbal instructions from a remote location and the robot follows them, clarifying possible misunderstandings as needed via dialogue. We found the division of labor between wizards to be workable, which holds promise for future software development.