It was reported yesterday by Digitimes that Google registered the interactive device A4R-GUIK2 with the Federal Communications Commission (FCC) in the United States. The device has a screen that supports Bluetooth, Wi-Fi, Zigbee and Soli radar gesture sensing technology, and is likely to be the new Nest Hub smart screen.

Coincidentally, the U.S. Patent Office published one of Google's patents related to their Soli radar sensing technology titled " Gesture Recognition Using Multiple Antenna" on December 17, 2020.

Google's summary in-part notes that "Various embodiments wirelessly detect micro gestures using multiple antennas of a gesture sensor device. At times, the gesture sensor device transmits multiple outgoing radio frequency (RF) signals, each outgoing RF signal transmitted via a respective antenna of the gesture sensor device. The outgoing RF signals are configured to help capture information that can be used to identify micro-gestures performed by a hand. The gesture sensor device captures incoming RF signals generated by the outgoing RF signals reflecting off of the hand, and then analyzes the incoming RF signals to identify the micro-gesture."

Google's patent FIG. 1 below illustrates an example environment #100 in which wireless hand gesture detection can be employed. The example environment includes a computing device #102 having a gesture sensor component #106 capable of wirelessly sensing gestures performed by hand; FIG. 4 illustrates example environment 400 in which multiple antenna are used to ascertain information about a target object.

Google's patent was originally granted in April 2016. The December 17, 2020 patent is a continuation patent that updates their patent claims. Just a few of the new patent claims are presented below that place heavy emphasis on machine-learning.

Patent Claim # 1: "A device configured to identify a gesture associated with a target object, the device comprising: a gesture sensor component configured to receive a plurality of incoming RF signals generated by at least one outgoing RF signal reflecting off the target object, the gesture sensor component comprising: a digital signal processing component configured to process a set of data originating from the incoming RF signals to extract information about the target object corresponding to at least two points in time; and a machine-learning component configured to: receive the information extracted by the digital signal processing component; and process the information to identify the gesture."

Patent Claim #7: "A device configured to identify a micro-gesture performed by a hand, the device comprising: a gesture sensor component configured to receive a plurality of incoming RF signals generated by at least one outgoing RF signal reflecting off the hand, the gesture sensor component comprising: a digital signal processing component configured to process a set of data originating from the incoming RF signals to extract information about the hand; and a machine-learning component configured to: receive the information extracted by the digital signal processing component; and process the information to identify the micro-gesture."

Patent Claim #14: "A device configured to identify a gesture performed by a user, the device comprising: a gesture sensor component configured to receive a plurality of incoming RF signals generated by at least one outgoing RF signal reflecting off two or more portions of the user, the gesture sensor component comprising: a digital signal processing component configured to process a set of data originating from the incoming RF signals to extract information about movements of each of the portions of the user; and a machine-learning component configured to: receive the information extracted by the digital signal processing component; and process the information to identify the gesture, the gesture comprising a relative movement between the portions of the user."

Patent Claim #20: "The device as recited in claim 19, wherein at least one application programming interface of the application programming interfaces is configured to perform at least one of: configuring transmission parameters associated with the outgoing RF signal; configuring the digital signal processing component to process the set of data originating from the incoming RF signals to extract the information about the movements of each of the portions of the user; configuring the machine-learning component to process the information to identify the gesture; or enabling registration for an event notification when the gesture is detected."

For more details, check out Google's Soli continuation patent 20200393912 to review all of their new patent claims.

Apple has been working on in-air gesturing for years with technology gained by acquiring the Israeli firm PrimeSense that was instrumental in delivering 3D Face ID technology. Here are three patents covering in-air gesturing: 01, 02, 03. You could review Patently Apple's archives on in-air gesturing for more examples. In most cases, it appears that Apple is using an alternative methodology related to direct Time-of-Flight (ToF).

Where Apple has directly linked to using "radar" technology was revealed on December 15, 2020 in our patent report titled "Apple Wins Patent for Advanced Presence Technology that could ID users without a Password or use of Biometrics."