Litcius/Paper detail

Graspable AI: Physical Forms as Explanation Modality for Explainable AI

Maliheh Ghajargar, Jeffrey Bardzell, Alison Smith, Kristina Höök, Peter Gall Krogh

202220 citationsDOIOpen Access PDF

Abstract

Explainable AI (XAI) seeks to disclose how an AI system arrives at its outcomes. But the nature of the disclosure depends in part on who needs to understand the AI and the available explanation modalities (e.g., verbal and visual). Users’ preferences regarding explanation modalities might differ, as some might prefer spoken explanations compared to visual ones. However, we argue for broadening the explanation modalities, to consider also tangible and physical forms. In traditional product design, physical forms have mediated people’s interactions with objects; more recently interacting with physical forms has become prominent with IoT and smart devices, such as smart lighting and robotic vacuum cleaners. But how tangible interaction can support AI explanations is not yet well understood.

Topics & Concepts

Modality (human–computer interaction)Computer scienceArtificial intelligenceCognitive sciencePsychologyExplainable Artificial Intelligence (XAI)Data Visualization and AnalyticsAnomaly Detection Techniques and Applications
Graspable AI: Physical Forms as Explanation Modality for Explainable AI | Litcius