What is it about?
In Augmented Reality (AR), placement of virtual objects is critical for accessibility. If objects drift out of view or are hard to reach, interaction breaks down. We built a machine learning system that learns from human demonstrations to keep objects optimally positioned and adapt to movement. Tested with nonspeaking autistic users, it enabled accurate, dynamic placement of a virtual letterboard for communication.
Featured Image
Photo by Vitaly Gariev on Unsplash
Read the Original
This page is a summary of: Personalized Adaptive Virtual Object Placement in AR for Nonspeaking Autistic Users Using Behavioural Cloning, ACM Transactions on Interactive Intelligent Systems, December 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3779216.
You can read the full text:
Contributors
The following have contributed to this page
