Conceptualizing the future home interface with a focus on gesture.

This project envisions how intelligent agent-based systems might seamlessly integrate into future homes by 2030. In 2023, we explored how daily interactions could evolve with LLM-driven agents, where voice becomes the main interface but visual displays still play a crucial role in communicating system awareness and transparency.

Through speculative scenarios like morning routines and deliveries, we visualized how AI could proactively collaborate with users—projecting contextual information onto everyday surfaces and responding naturally to conversation.

In early stage we explored how “use everywhere” can be achieved through context-aware visual interactions — where the system intelligently places information in the user’s environment, adapting to their activity and focus. It visualizes how multiple interfaces can coexist seamlessly — displaying relevant information like workouts, schedules, and music — where it feels most natural to the user.

Vision Research

We conceptualized a way to break screen borders to use the system everywhere in the room by projection as an interface medium. Meanwhile, combining voice inputs, users is able to use smart home applications without physical contact to expand use cases and use everywhere.
‍
In this project, we focused on designing conversational AI and the gesture-voice input methods. My main contributions included gesture research, prototyping animations, and the design of AI visualizations.

We explored how gesture and voice could replace traditional touch-based interaction in future home systems. Instead of tapping screens, users could simply reach toward projected interfaces or give a verbal command, allowing the system to adapt interface size and position dynamically.

Our prototype, built with projection and motion detection, mimicked how these spatial interactions might feel in a real home environment.