An Introduction to Causal Inference Methods for Observational Human-Robot Interaction Research

TL;DR

This paper introduces causal inference methods tailored for observational human-robot interaction research, addressing the limitations of traditional experimental approaches and providing practical guidance and code resources.

Contribution

It presents a tutorial on applying causal inference techniques to observational HRI data, expanding analytical tools for researchers in real-world settings.

Findings

Causal inference methods can identify causal relationships in observational HRI data.

Graphical models help visualize and understand causal structures in HRI.

Practical code examples facilitate adoption of causal methods in HRI research.

Abstract

Quantitative methods in Human-Robot Interaction (HRI) research have primarily relied upon randomized, controlled experiments in laboratory settings. However, such experiments are not always feasible when external validity, ethical constraints, and ease of data collection are of concern. Furthermore, as consumer robots become increasingly available, increasing amounts of real-world data will be available to HRI researchers, which prompts the need for quantative approaches tailored to the analysis of observational data. In this article, we present an alternate approach towards quantitative research for HRI researchers using methods from causal inference that can enable researchers to identify causal relationships in observational settings where randomized, controlled experiments cannot be run. We highlight different scenarios that HRI research with consumer household robots may involve to contextualize how methods from causal inference can be applied to observational HRI research. We then provide a tutorial summarizing key concepts from causal inference using a graphical model perspective and link to code examples throughout the article, which are available at https://gitlab.com/causal/causal_hri. Our work paves the way for further discussion on new approaches towards observational HRI research while providing a starting point for HRI researchers to add causal inference techniques to their analytical toolbox.