Year: 2025
Type: conference-paper
Abstract: As a Large Language Object (LLO), Roulettective is an AI-driven detective game machine that reinvents the vintage carousel slide projector as a tangible interface for immersive gaming.The project explores the projector's potential in a detective game context, creating new usage scenarios by reprogramming its physical interaction mechanisms and integrating AI-driven gameplay.It further transforms this forgotten artifact into a multimodal, immersive, customizable, intuitive, and co-creative interface through AI-generated narratives, visuals, and sound.By revisiting physical interactions lost in the shift to screen-based computing, Roulettective reframes obsolete artifacts as platforms for new multimodal AI experiences.It introduces AI reinvention as a design toolkit as a generalizable framework.
Authors: Yuhan Wang, Jianuo Xuan
Institutions: Harvard University, Massachusetts Institute of Technology
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W7084047459