US 12,483,286 B2
Reinforcement learning receiver front-end
Kevin Wesley Kobayashi, Redondo Beach, CA (US); Paul Edward Gorday, West Palm Beach, FL (US); Charles Forrest Campbell, Dallas, TX (US); and Gangadhar Burra, Fremont, CA (US)
Assigned to Qorvo US, Inc., Greensboro, NC (US)
Filed by Qorvo US, Inc., Greensboro, NC (US)
Filed on Jul. 17, 2023, as Appl. No. 18/353,163.
Claims priority of provisional application 63/483,820, filed on Feb. 8, 2023.
Claims priority of provisional application 63/394,804, filed on Aug. 3, 2022.
Prior Publication US 2024/0048166 A1, Feb. 8, 2024
Int. Cl. H04B 1/10 (2006.01); H04B 1/06 (2006.01); H04B 1/12 (2006.01)
CPC H04B 1/123 (2013.01) 42 Claims
OG exemplary drawing
 
1. A reinforcement learning reconfigurable receiver front-end (RL-RXFE) comprising:
a low-noise amplifier (LNA) having an amplifier input and an amplifier output, wherein the LNA is configured to respond to adjustable supply voltage VDD and bias voltages; and
reinforcement learning processing circuitry configured to receive spectrum information from an LNA-input detection node coupled to the amplifier input, spectrum information from an LNA-output detection node coupled to the amplifier output, distortion by-product information generated by a baseband distortion by-product detector/sensor, and LNA dynamic information, wherein the reinforcement learning processing circuitry is configured both to perform reinforcement learning and to generate control signals received by the LNA in response to the spectrum information, the distortion by-products information, and the LNA dynamic information.