Warning Signals for Poor Performance Improve Human-Robot Interaction

Rik Van Den Brule,Ron Dotsch,Daniel H J Wigboldus,Pim Haselager,Gijsbert Bijlstra

doi:10.5898/jhri.5.2.van_den_brule

Rik Van Den Brule, Ron Dotsch + Show 3 more

Open Access

https://doi.org/10.5898/jhri.5.2.van_den_brule

Copy DOI

Abstract

The present research was aimed at investigating whether human-robot interaction (HRI) can be improved by a robot's nonverbal warning signals. Ideally, when a robot signals that it cannot guarantee good performance, people could take preventive actions to ensure the successful completion of the robot's task. In two experiments, participants learned either that a robot's gestures predicted subsequent poor performance, or they did not. Participants evaluated a robot that uses predictive gestures as more trustworthy, understandable, and reliable compared to a robot that uses gestures that are not predictive of their performance. Finally, participants who learned the relation between gestures and performance improved collaboration with the robot through prevention behavior immediately after a predictive gesture. This limits the negative consequences of the robot's mistakes, thus improving the interaction.

Highlights

Robotic autonomous systems are becoming more common in everyday life
The present results demonstrate that a predictable robot is preferred despite its occasional poor performance, as long as it generally signals that a mistake might occur
We believe that the current results provide novel insights in the use of contingency learning in HRI

Summary

Introduction

Robotic autonomous systems are becoming more common in everyday life. Successful robotic applications must be capable of operating in versatile, dynamic environments, and of interacting with people present. As such, they can be considered socially interactive robots (Fong, Nourbakhsh, & Dautenhahn, 2003). The uncontrolled domestic environment they operate in can change quickly, and a task that is relatively simple in one situation might become increasingly complex in other situations. An otherwise simple task for a butler robot such as serving a glass of water may become quite difficult when its tactile sensors are dirty and it can no longer feel how well it holds the glass. Likewise, handing over a glass of beer may be easy in a situation where the receiver is alone and sitting quietly behind a table but much more complicated once a party has started and the receiver is found dancing on a crowded floor

Methods

Results

Discussion

Conclusion