A system that surfaces road hazards before you drive them. It pulls Street View imagery every 50 metres along a chosen route and has AI analyse each point from several angles — blind corners, road surface, visibility — scoring risk on a ten-point scale. The result is a colour-coded map you can question spot by spot in chat.
Judges valued the novelty of predicting hazards from map data and the social weight of reducing traffic accidents. They also expressed hope that the project would grow into a form that many more people could use.
The cleverness may lie in how ordinary the ingredients are. Street View and route search are APIs anyone can call; what turns them into an inspection tool is the simple rule of sampling every 50 metres. The second factor is the output. Expressing risk as a ten-point score painted onto a map means it can be read at a glance without any expertise. For a runner-up award, that combination of a fresh premise and legibility looks like what carried it.
See all winners of 第3回 AI Agent 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).