REFLEX Dataset: A Multimodal Dataset of Human Reactions to Robot Failures and Explanations

TL;DR

REFLEX is a comprehensive multimodal dataset capturing human reactions to robot failures and explanations, aiming to advance human-robot interaction research and improve robot adaptability and user satisfaction.

Contribution

The paper introduces REFLEX, a novel dataset that includes rich annotations of human responses to robot failures and explanations, facilitating research on adaptive and robust human-robot collaboration.

Findings

Dataset includes diverse failure types and explanation strategies.

Reactions evolve over long-term interactions, showing adaptation.

Rich multimodal annotations enable detailed analysis of human responses.

Abstract

This work presents REFLEX: Robotic Explanations to FaiLures and Human EXpressions, a comprehensive multimodal dataset capturing human reactions to robot failures and subsequent explanations in collaborative settings. It aims to facilitate research into human-robot interaction dynamics, addressing the need to study reactions to both initial failures and explanations, as well as the evolution of these reactions in long-term interactions. By providing rich, annotated data on human responses to different types of failures, explanation levels, and explanation varying strategies, the dataset contributes to the development of more robust, adaptive, and satisfying robotic systems capable of maintaining positive relationships with human collaborators, even during challenges like repeated failures.