An AI partner for finding things around the house. It watches the room at intervals, keeping a log of footage, so asked where the keys are it reports not just a place but a state, such as hidden under a magazine. If they are absent, it reasons from calendar entries to suggest candidates, and turns its camera with a servo.
Judges noted it tackles misplaced belongings with an AI approach unlike existing trackers, and called the agent-to-agent communication design and inference from footage logs and activity history technically interesting, with high completeness.
Finding lost things has mostly meant tagging whatever you expect to lose. This project stands on the other side and watches the room, so it also reaches objects nobody thought to tag; the shift in premise is doing real work. Reasoning from calendar entries when something is simply not in the footage patches the obvious weakness of a camera-based approach. Pulling software and hardware, down to a camera that turns itself, into one experience likely helped the demo land.
See all winners of 第4回 Agentic AI Hackathon with Google Cloud →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).