XAIR: A Framework of Explainable AI in Augmented Reality
Abstract
Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems. With Augmented Reality (AR) becoming more integrated in daily lives, the role of XAI also becomes essential in AR because end-users will frequently interact with intelligent services. However, it is unclear how to design effective XAI experiences for AR. We propose XAIR, a design framework that addresses "when", "what", and "how" to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature review of XAI and HCI research, a large-scale survey probing 500+ end-users' preferences for AR-based explanations, and three workshops with 12 experts collecting their insights about XAI design in AR. XAIR's utility and effectiveness was verified via a study with 10 designers and another study with 12 end-users. XAIR can provide guidelines for designers, inspiring them to identify new design opportunities and achieve effective XAI designs in AR.
Cite
@article{arxiv.2303.16292,
title = {XAIR: A Framework of Explainable AI in Augmented Reality},
author = {Xuhai Xu and Mengjie Yu and Tanya R. Jonker and Kashyap Todi and Feiyu Lu and Xun Qian and João Marcelo Evangelista Belo and Tianyi Wang and Michelle Li and Aran Mun and Te-Yen Wu and Junxiao Shen and Ting Zhang and Narine Kokhlikyan and Fulton Wang and Paul Sorenson and Sophie Kahyun Kim and Hrvoje Benko},
journal= {arXiv preprint arXiv:2303.16292},
year = {2023}
}
Comments
Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems