Project Soli

Designing feasible prototypes and data visualizations for a new interaction sensor using radar technology.

Project Soli at Google ATAP is developing a new interaction sensor using radar technology. The sensor can track sub-millimeter motions at high speed and accuracy. It fits onto a chip, can be produced at scale and built into small devices and everyday objects.

Project Soli chip evolution

Studio NAND was brought in from the get-go and worked for over two years with many versions of the evolving sensor. Going beyond renderings, we created feasible use cases and working prototypes using the chip and trained these machines to work with self-designed gesture sets, getting back real actionable data to further improve the sensor.

At a later stage, Studio NAND handled the full software development kit documentation including demos, gesture kit explication, and creating wrappers in lower level languages.

The hand is the ultimate input device. It’s extremely precise, it’s extremely fast, and it’s very natural for us to use it.
Dr. Ivan Poupyrev
Illustrations for the machine learning tutorial


Video Ottica Project lead Dr. Ivan Poupyrev Core team Nicholas Gillian, Hakim Raja, Erik Olson, Jaime Lien, Patrick Amihood and Emre Karagozler. Our day to day work has been guided by Carsten Schwesig and Fumi Yamazaki.

In collaboration with Tim Gferer, Arturo Castro, Tomek Ness, Jochen Maria Weber, Sebastian An