Infineon Technologies Ag

Mate Andras Toth

Paul Meissner

Alexander Melzer

Franz Pernkopf

Johanna Rock

Wolfgang Roth

Christian Schmid

Elmar Messner

Alexander Fuchs

A radar device may include 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 may comprise a plurality of signal segments. The radar device may include a neural network comprising a plurality of layers to process the plurality of signal segments. Each layer of the plurality of layers may have one or more neurons. The plurality of layers may process the plurality of signal segments using weighting factors having values selected from a predetermined set of discrete values. At least one neuron in an output layer of the plurality of layers may provide an output value that indicates whether a respective signal segment or a sample, associated with the at least one neuron, is overlaid with an interfering signal.

FMCW radar with interference signal suppression using artificial neural network

A radar device may include a radar transmitter to output a radio frequency (RF) transmission signal including a plurality of frequency-modulated chirps. The radar device may include a radar receiver to receive an RF radar signal, and generate, based on the RF radar signal, a dataset including a set of digital values, the dataset being associated with a chirp or a sequence of successive chirps. The radar device may include a neural network to filter the dataset to reduce an interfering signal included in the dataset, the neural network being a convolutional neural network. At least one layer of the neural network may be a complex-valued neural network layer includes complex-valued weighting factor, where the complex-valued neural network layer is configured to perform one or more operations according to a complex-valued computation.

A method for a radar device is described below. According to an example implementation, the method comprises transmitting an RF transmission signal that comprises a plurality of frequency-modulated chirps, and receiving an RF radar signal and generating a dataset containing in each case a particular number of digital values based on the received RF radar signal. A dataset may in this case be associated with a chirp or a sequence of successive chirps. The method furthermore comprises filtering the dataset by way of a neural network to which the dataset is fed in order to reduce an interfering signal contained therein. A convolutional neural network is used as the neural network.

In accordance with an embodiment, a method of operating a radar system includes activating a transmitter to transmit a radar signal during a first time period, receiving a reflection of the radar signal from a radar antenna, downconverting the reflected radar signal, and digitally processing the downconverted reflected radar signal within a first frequency bandwidth using a first signal path. The method also includes deactivating the transmitter during a second time period, receiving a second signal from the radar antenna during the second time period, downconverting the second signal, measuring a power of the downconverted second signal within a second frequency bandwidth using a second signal path different from the first signal path, and determining an interference metric based on measuring the power.

System and method for determining interference in a radar system

A method is described that can be used in a radar system. In accordance with one exemplary embodiment, the method includes calculating a first spectrum, which represents a spectrum of a segment of a complex baseband signal. The segment is assignable to a specific chirp of a chirp sequence contained in a first RF radar signal. The method further includes estimating a second spectrum, which represents a spectrum of an interference signal contained in the complex baseband signal, based on a portion of the first spectrum that is assigned to negative frequencies.

FMCW radar with interference signal suppression

The description below relates to a method for a radar system that can be used to detect perturbations in the received radar signal. According to an example implementation, the method comprises providing a digital radar signal using a radar receiver, wherein the digital radar signal comprises a multiplicity of segments; calculating an envelope signal that represents the envelope of a segment of the digital radar signal; and ascertaining a time of the onset of an interference signal contained in the considered segment of the digital radar signal by using at least one statistical parameter of the envelope signal.

Detection of interference-induced perturbations in FMCW radar systems

A method is described below which can be used in a radar system. According to one example implementation, the method comprises providing a digital baseband signal using a radar receiver. The baseband signal comprises a plurality of segments, wherein each segment is assigned to a chirp of an emitted chirp sequence and each segment comprises a specific number of samples. For each signal sequence of n samples of the segments, where n in each case denotes a specific sample position within the respective segment, the method comprises the following: detecting interference-affected samples of the signal sequence; splitting the signal sequence into two or more sub-band signal sequences, wherein each sub-band signal sequence is assigned in each case to a frequency sub-band; replacing interference-affected samples in the two or more sub-band signal sequences in each case with a value which is based on adjacent samples in order to obtain corrected sub-band signal sequences; and determining a corrected signal sequence of n samples of the segments based on the corrected sub-band signal sequences.

Growing community of inventors

Graz, Austria

Mate Andras Toth