Patents by Inventor Maximilian Eschbaumer
Maximilian Eschbaumer has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 12189053Abstract: According to various examples, a radar system is described comprising a radar receiver configured to perform sampling of a radio reception signal and to generate a sample for each of a plurality of sampling times, a machine learning model configured to generate, for each of one or more additional sampling times, a sample from the samples generated for the sampling times and an object detector configured to perform range estimation of one or more detected objects using the samples generated by the machine learning model.Type: GrantFiled: April 27, 2022Date of Patent: January 7, 2025Assignee: Infineon Technologies AGInventors: Simon Achatz, Maximilian Eschbaumer
-
Patent number: 12153125Abstract: According to various embodiments, a radar system is described including a direction of arrival pre-processor configured to, for a detected peak, obtain a Doppler Fourier transform result vector, generate a spatial covariance matrix for the Doppler Fourier transform result vector, and generate an additional spatial covariance matrix by inputting the spatial covariance matrix to a machine learning model trained to predict, from an input spatial covariance matrix, an output spatial covariance matrix such that the output spatial covariance matrix corresponds to a different chirp center frequency than the input covariance spatial covariance matrix and including a direction of arrival estimator configured to perform direction-of-arrival estimation using the additional spatial covariance matrix.Type: GrantFiled: April 27, 2022Date of Patent: November 26, 2024Assignee: Infineon Technologies AGInventors: Simon Achatz, Maximilian Eschbaumer
-
Patent number: 12099110Abstract: According to various embodiments, a radar system is described comprising a radar receiver configured to receive radio signals, wherein each radio signal is associated with a channel of a plurality of channels, a peak detector configured to perform peak detection using the received radio signals, wherein each detected peak corresponds to a detected object and a direction of arrival estimator configured to, for a detected peak, generate a vector having, for each of the channels, an entry specifying a Doppler Fourier transform result for the channel, supply the vector to a machine learning model trained to output, for each of one or more additional channels, an entry specifying a predicted Doppler Fourier transform result corresponding to the additional channel and perform direction-of-arrival estimation using an output from the machine learning model which the machine learning model outputs in response to being supplied with the vector.Type: GrantFiled: April 19, 2022Date of Patent: September 24, 2024Assignee: Infineon Technologies AGInventors: Simon Achatz, Maximilian Eschbaumer
-
Publication number: 20230384418Abstract: Systems, methods, and circuitries are provided for calibrating a radar system to compensate for a channel offset. In one example, a method is disclosed for processing radar signals with a radar device. The method includes including receiving respective radar signals from respective virtual receive channels, wherein each virtual receive channel corresponds to a combination of a transmit antenna element and a receive antenna element of an antenna element array. Respective received radar data is generated from the respective radar signals and the radar date is processed to identify one or more stationary objects. Based on the radar data, an estimated radar device motion relative to the one or more stationary objects is determined. A difference between the estimated radar device motion and an expected motion of the radar device is determined and a correction vector is determined based on the difference. The correction vector to is applied to subsequent radar data.Type: ApplicationFiled: May 31, 2022Publication date: November 30, 2023Inventors: Mayeul Jeannin, Maximilian Eschbaumer, Farhan Bin Khalid, Dian Tresna Nugraha, Andre Roger
-
Publication number: 20230350011Abstract: According to various examples, a radar system is described comprising a radar receiver configured to perform sampling of a radio reception signal and to generate a sample for each of a plurality of sampling times, a machine learning model configured to generate, for each of one or more additional sampling times, a sample from the samples generated for the sampling times and an object detector configured to perform range estimation of one or more detected objects using the samples generated by the machine learning model.Type: ApplicationFiled: April 27, 2022Publication date: November 2, 2023Inventors: Simon ACHATZ, Maximilian ESCHBAUMER
-
Publication number: 20230350013Abstract: According to various embodiments, a radar system is described comprising a radar receiver configured to receive radio signals, a range Fourier transform stage configured to generate, for each of a plurality of chirps, a vector of range Fourier transform coefficients, a machine learning model configured to generate, for each of one or more additional chirps, a vector of range Fourier transform coefficients from the vectors of Fourier transform coefficients generated for the plurality of chirps, and an object detector configured to perform velocity estimation of one or more detected objects using the Fourier transform coefficients generated by the machine learning model.Type: ApplicationFiled: April 27, 2022Publication date: November 2, 2023Inventors: Simon ACHATZ, Maximilian ESCHBAUMER
-
Publication number: 20230350054Abstract: According to various embodiments, a radar system is described including a direction of arrival pre-processor configured to, for a detected peak, obtain a Doppler Fourier transform result vector, generate a spatial covariance matrix for the Doppler Fourier transform result vector, and generate an additional spatial covariance matrix by inputting the spatial covariance matrix to a machine learning model trained to predict, from an input spatial covariance matrix, an output spatial covariance matrix such that the output spatial covariance matrix corresponds to a different chirp center frequency than the input covariance spatial covariance matrix and including a direction of arrival estimator configured to perform direction-of-arrival estimation using the additional spatial covariance matrix.Type: ApplicationFiled: April 27, 2022Publication date: November 2, 2023Inventors: Simon ACHATZ, Maximilian ESCHBAUMER
-
Publication number: 20230350056Abstract: According to various embodiments, a radar system is described including a first radar processing device and a second radar processing device, wherein the first radar processing device is configured to generate radar data and to transmit the radar data partially to the second radar processing device for further processing, wherein the first radar processing device is configured to omit parts of the radar data from the transmission and wherein the second radar processing device is configured to reconstruct the omitted parts using a machine learning model trained to supplement radar data with additional radar data and is configured to further process the transmitted parts of the radar data in combination with the additional radar data.Type: ApplicationFiled: April 27, 2022Publication date: November 2, 2023Inventors: Simon ACHATZ, Maximilian ESCHBAUMER
-
Publication number: 20230333233Abstract: According to various embodiments, a radar system is described comprising a radar receiver configured to receive radio signals, wherein each radio signal is associated with a channel of a plurality of channels, a peak detector configured to perform peak detection using the received radio signals, wherein each detected peak corresponds to a detected object and a direction of arrival estimator configured to, for a detected peak, generate a vector having, for each of the channels, an entry specifying a Doppler Fourier transform result for the channel, supply the vector to a machine learning model trained to output, for each of one or more additional channels, an entry specifying a predicted Doppler Fourier transform result corresponding to the additional channel and perform direction-of-arrival estimation using an output from the machine learning model which the machine learning model outputs in response to being supplied with the vector.Type: ApplicationFiled: April 19, 2022Publication date: October 19, 2023Inventors: Simon ACHATZ, Maximilian ESCHBAUMER
-
Patent number: 11789114Abstract: A method for the use in a radar system comprises: receiving an RF radar signal; down-converting the received RF radar signal into a base band using a frequency-modulated local oscillator signal including a scanning chirp having a higher bandwidth than a regular chirp bandwidth; generating a digital base band signal based on the down-converted RF radar signal, the digital base band signal including a sequence of samples associated with the scanning chirp; identifying, in the sequence of samples, impaired samples, which are affected by interference; and selecting—based on the position of the impaired samples within the sequence of samples—a sub-band, which has the regular chirp bandwidth, for transmitting chirps of chirp frame used for measurement data acquisition.Type: GrantFiled: December 8, 2020Date of Patent: October 17, 2023Assignee: Infineon Technologies AGInventors: Andre Roger, Markus Bichl, Maximilian Eschbaumer, Farhan Bin Khalid, Paul Meissner
-
Publication number: 20220342039Abstract: According to at least one embodiment, a MIMO radar arrangement includes a radar receiver configured to generate radar reception data from radio receive signals received by a plurality of radar receive antennas. The arrangement further includes one or more signal processors configured to: generate frequency domain data for a range-Doppler bin based on the radar reception data and determine one or more peaks from the generated frequency domain data. The radar arrangement further includes a trained machine learning module configured to generate, using frequency domain data corresponding to each of the of the one or more determined peaks as input, one or more output values indicating a number of detected objects within each range-Doppler bin.Type: ApplicationFiled: April 14, 2022Publication date: October 27, 2022Inventors: Maximilian Eschbaumer, Simon Achatz
-
Patent number: 11437971Abstract: Embodiments relate to a transformer-based impedance matching network that may dynamically change its characteristic impedance by engaging different inductor branches on a primary side and optionally, on the secondary side. A primary side transformer circuit includes a primary inductor (311) and secondary inductor (321) configured to provide impedance matching over a first frequency band. One or more additional inductor branches (314A, 314B, are switchably coupled to either or both of the primary and secondary inductors to modify the impedance matching characteristics over additional operating frequencies. One or more LC filter branches (321, 322, 326, 327, 336, 330) can be included at the output of the secondary side to filter harmonic frequencies in each of the operating frequency bands.Type: GrantFiled: June 27, 2018Date of Patent: September 6, 2022Assignee: INTEL CORPORATIONInventors: Chuanzhao Yu, Maximilian Eschbaumer
-
Publication number: 20210364596Abstract: It is suggested to process radar signals including: (i) receiving reception signals via at least one antenna of a first receiving circuit; (ii) determining an interim result by processing the reception signals via a frequency transformation; (iii) determining an error compensation vector based on the interim result and an expected characteristic; and (iv) applying the error compensation vector on other reception signals that have been processed via the frequency transformation.Type: ApplicationFiled: May 19, 2021Publication date: November 25, 2021Inventors: Andre Roger, Simon Achatz, Dian Tresna Nugraha, Ljudmil Anastasov, Markus Bichl, Mayeul Jeannin, Maximilian Eschbaumer
-
Publication number: 20210190905Abstract: A method for the use in a radar system comprises: receiving an RF radar signal; down-converting the received RF radar signal into a base band using a frequency-modulated local oscillator signal including a scanning chirp having a higher bandwidth than a regular chirp bandwidth; generating a digital base band signal based on the down-converted RF radar signal, the digital base band signal including a sequence of samples associated with the scanning chirp; identifying, in the sequence of samples, impaired samples, which are affected by interference; and selecting—based on the position of the impaired samples within the sequence of samples—a sub-band, which has the regular chirp bandwidth, for transmitting chirps of chirp frame used for measurement data acquisition.Type: ApplicationFiled: December 8, 2020Publication date: June 24, 2021Inventors: Andre ROGER, Markus BICHL, Maximilian ESCHBAUMER, Farhan Bin KHALID, Paul MEISSNER
-
Patent number: 11018669Abstract: Methods, systems, and circuities for selectively connecting an RF signal to front end circuitry and selectively attenuating the RF signal are disclosed. In one example, an interface circuitry includes switching circuitry and attenuator circuitry. The switching circuitry is connected in series between an output of an amplifier and a front end circuitry configured to transmit a radio frequency (RF) signal output by the amplifier. The switching circuitry connects the output of the amplifier to a selected one or more front end circuitry inputs to create one or more signal paths. The attenuator circuitry is connected between the output of the amplifier and ground to create an attenuation path in a shunt configuration relative to the one or more signal paths. The attenuator circuitry is configured to attenuate the RF signal.Type: GrantFiled: March 7, 2018Date of Patent: May 25, 2021Assignee: Intel IP CorporationInventor: Maximilian Eschbaumer
-
Publication number: 20210119596Abstract: Embodiments relate to a transformer-based impedance matching network that may dynamically change its characteristic impedance by engaging different inductor branches on a primary side and optionally, on the secondary side. A primary side transformer circuit includes a primary inductor (311) and secondary inductor (321) configured to provide impedance matching over a first frequency band. One or more additional inductor branches (314A, 314B, are switchably coupled to either or both of the primary and secondary inductors to modify the impedance matching characteristics over additional operating frequencies. One or more LC filter branches (321, 322, 326, 327, 336, 330) can be included at the output of the secondary side to filter harmonic frequencies in each of the operating frequency bands.Type: ApplicationFiled: June 27, 2018Publication date: April 22, 2021Inventors: Chuanzhao YU, Maximilian ESCHBAUMER
-
Publication number: 20200403615Abstract: Methods, systems, and circuities for selectively connecting an RF signal to front end circuitry and selectively attenuating the RF signal are disclosed. In one example, an interface circuitry includes switching circuitry and attenuator circuitry. The switching circuitry is connected in series between an output of an amplifier and a front end circuitry configured to transmit a radio frequency (RF) signal output by the amplifier. The switching circuitry connects the output of the amplifier to a selected one or more front end circuitry inputs to create one or more signal paths. The attenuator circuitry is connected between the output of the amplifier and ground to create an attenuation path in a shunt configuration relative to the one or more signal paths. The attenuator circuitry is configured to attenuate the RF signal.Type: ApplicationFiled: March 7, 2018Publication date: December 24, 2020Inventor: Maximilian Eschbaumer