Wavy Abstract Background

Fairness and Transparency in HRI

Algorithms, Methods, and Metrics

2022 ACM/IEEE International Conference on Human-Robot Interaction Workshop

March 7, 2022

What is this workshop about?

As robots become more ubiquitous across human spaces, it is becoming increasingly relevant for researchers to ask the question, "how can we ensure that we are designing robots to be sufficiently equipped to treat people fairly?''. This workshop brings together researchers across the fields of Human-Robot Interaction (HRI), fairness in machine learning, design, and transparency in AI to shed light on the relevant methodological challenges surrounding issues of fairness and transparency in HRI.

 

In our workshop, we will attempt to identify synergies between these various fields. In particular, we will focus on how HRI can leverage these existing rich body of work to guide the formalization of fairness metrics and methodologies. Another goal of the workshop is to foster a community of interdisciplinary researchers to encourage collaboration. The complexity in defining fairness lies in its context sensitive nature, as such we look to the influx of definitions from the field of fairness in artificial intelligence, design, and organizational psychology to derive a set of definitions that could serve as guidelines for researchers in HRI.  

Organizing Team

Houston Claure

Cornell University

Mai Lee Chang

University of Texas at Austin

Seyun Kim

Carnegie Mellon University

Daniel Omeiza

University of Oxford

Martim Brandão

King’s College London

Min Kyung Lee

University of Texas at Austin

Malte Jung

Cornell University

Abstract Futuristic Background

Relevant topics of interest for this workshop include but are not limited to: 

- Trustworthy AI
- Trust and Human-Robot Interaction 
- Ethics implications in HRI
- Ethical design of robotic systems
- Age/race/gender-biased robots
- Transparency in HRI
- Human biases in HRI
- Development and study of fair machine learning models in robotics
- Interaction design and explainable AI
- Metrics for studying fairness
- Fairness in resource allocation
- Fairness in Human-robot teams