Material recognizing radar built using Google Soli

Google Project Soli Beta DevKit

Last year, search engine giant, Google unveiled a new tiny chipset that goes by the name ‘Project Soli’, which detects gestures and movements with radar.

Now, the latest news is that the scientist from St. Andrews university built RadarCat, a device driven by machine language that  identifies object and material just by getting close to it.

project soli

Based on radar apparatus concept, the RadarCat has been built using specially made close-range radar built using technology from Google’s Project Soli alpha developer kit. As it is based on Machine learning, the precision of the device will increase by time and helps in not only figuring out different objects like metal and wood, but also on a general basis, such as a phone, adapters, and laptops.

Moreover, with a host machine to run its software, it can be trained to pick out specific objects by their proper name. In a demo video, the researcher places a Nexus 5 on the radar plate and it identifies it correctly. Following Nexus 5, the researcher tried on Nexus 10 and other fruits including orange and apple and got the same result.

Source | Via