US 12,032,089 B2
FMCW radar with interference signal suppression using artificial neural network
Paul Meissner, Feldkirchen bei Graz (AT); Franz Pernkopf, Graz (AT); Johanna Rock, Graz (AT); Wolfgang Roth, Graz (AT); and Mate Andras Toth, Graz (AT)
Assigned to Infineon Technologies AG, Neubiberg (DE)
Filed by Infineon Technologies AG, Neubiberg (DE)
Filed on Jul. 8, 2020, as Appl. No. 16/923,916.
Application 16/923,916 is a continuation in part of application No. 16/817,385, filed on Mar. 12, 2020, granted, now 11,885,903.
Claims priority of application No. 102019106529.1 (DE), filed on Mar. 14, 2019.
Prior Publication US 2020/0341109 A1, Oct. 29, 2020
This patent is subject to a terminal disclaimer.
Int. Cl. G01S 7/295 (2006.01); G01S 7/02 (2006.01); G01S 7/282 (2006.01); G01S 7/41 (2006.01); G01S 13/02 (2006.01); G06N 3/063 (2023.01); G06N 3/08 (2023.01); G06N 3/084 (2023.01); G06N 5/04 (2023.01); G06N 5/046 (2023.01); G01S 7/35 (2006.01); G01S 13/34 (2006.01); G01S 13/44 (2006.01); G01S 13/58 (2006.01); G01S 13/931 (2020.01); G06N 3/045 (2023.01)
CPC G01S 7/023 (2013.01) [G01S 7/282 (2013.01); G01S 7/295 (2013.01); G01S 7/417 (2013.01); G01S 13/02 (2013.01); G06N 3/063 (2013.01); G06N 3/084 (2013.01); G06N 5/046 (2013.01); G01S 7/352 (2013.01); G01S 7/354 (2013.01); G01S 7/356 (2021.05); G01S 13/343 (2013.01); G01S 13/4454 (2013.01); G01S 13/584 (2013.01); G01S 13/931 (2013.01); G06N 3/045 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A radar device associated with a first vehicle, the radar device comprising:
a radar receiver to:
receive a radio frequency (RF) radar signal, and
generate a digital signal based on the RF radar signal, the digital signal comprising a plurality of signal segments; and
a neural network comprising a plurality of layers, including an input layer and an output layer, configured to process the plurality of signal segments, each layer of the plurality of layers having one or more neurons,
wherein the plurality of layers is configured to process the plurality of signal segments using quantized weighting factors having quantized values selected by the neural network from a predetermined set of discrete values, and
wherein at least one neuron of the output layer is configured to provide an output value that indicates whether a respective signal segment or a sample of the respective signal segment, associated with the at least one neuron of the output layer, is overlaid with an interfering signal generated by a radar sensor associated with a second vehicle different from the first vehicle.