XAIR: A Framework of Explainable AI in Augmented Reality
This addresses the need for clear XAI design guidelines in AR for end-users and designers, though it is incremental as it builds on existing XAI and HCI research.
The authors tackled the problem of designing effective explainable AI (XAI) experiences for augmented reality (AR) by proposing XAIR, a framework based on literature review, a survey of 500+ users, and expert workshops, which was verified through studies with designers and end-users.
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.