Google's TrackInspect relies on the phone's suite of accelerometers, magnetometers, and gyroscopes, as well as additional microphones mounted to subway cars to feel and listen for track defects. The tech giant is confident that AI models can be trained to supplement the work of human inspectors.

Anyone who has rode the New York City subway can tell you that it has a lot of problems, from strange noises to flammable debris on the tracks. Now, as is the solution for everything these days, the Metropolitan Transportation Authority (MTA) is testing how AI could improve the repair process with the help of six Google Pixel phones.

Google and MTA collaborated on a project using Pixel phones to detect subway anomalies. Pixel phones located problem spots 92% of the time, showing promise for future subway monitoring. We've been living with smartphones for so long that it's easy to forget just how complex these devices really are.