Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Examiner’s Note
For applicant’s benefit, portions of the cited reference(s) have been cited to aid in the review of the rejection(s). While every attempt has been made to be thorough and consistent within the rejection it is noted that the PRIOR ART MUST BE CONSIDERED IN ITS ENTIRETY, including disclosures that teach away from the claims. See MPEP 2141.02 VI.
“The use of patents as references is not limited to what the patentees describe as their own inventions or to the problems with which they are concerned. They are part of the literature of the art, relevant for all they contain.” In re Heck, 699 F.2d 1331, 1332-33, 216 USPQ 1038, 1039 (Fed. Cir. 1983) (quoting In re Lemelson, 397 F.2d 1006, 1009, 158 USPQ 275, 277 (CCPA 1968)). A reference may be relied upon for all that it would have reasonably suggested to one having ordinary skill in the art, including non-preferred embodiments. Merck & Co. v.Biocraft Laboratories, 874 F.2d 804, 10 USPQ2d 1843 (Fed. Cir.), cert. denied, 493 U.S. 975 (1989). See also Upsher-Smith Labs. v. Pamlab, LLC, 412 F.3d 1319, 1323, 75 USPQ2d 1213, 1215 (Fed. Cir. 2005) See MPEP 2123.
Response to Amendment
Applicant’s amendment filed 23 June 2026 is acknowledged and has been entered.
Claim rejections under 35 USC 101 have been overcome in view of the amendment.
Response to Arguments
Applicant’s argument filed 23 June 2026 has been fully considered but is moot in view of a new ground of rejection necessitated by Applicant’s amendment.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 7, 9, and 11-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Meuter et al. (US 2022/0026568 A1 newly cited “MEUTER”), in view of Evans et al. (US 2022/0404490 A1 previously cited “EVANS”).
Regarding claim 1, MEUTER discloses (Examiner’s note: What MEUTER does not disclose is ) a computer implemented method for determining a beam vector list for object detection, the method comprising the following steps carried out by computer hardware components: receiving radar data from at least one radar sensor of a vehicle (a method for detection of objects in a vicinity of a vehicle [0181]); (radar data may be acquired from a radar sensor [0181]); determining range information and velocity information based on the radar data (a plurality of features may be determined based on the radar data [0181]); (a 2D FFT (fast Fourier transform) may decompose the input signal for each antenna into frequency components and thus range and Doppler [0068]); a deep neural network (NN) architecture 1308 may provide processing, fusion and/or tracking, in order to obtain object tracks bounding boxes 1310, pedestrian tracks bounding boxes 1312, and/or a semantic segmentation map or guardrail segmentation 1314 [0141]); wherein a driver assistant system controls a system of the vehicle based on the detected at least one object in the environment of the vehicle (outputting an information of the objects detected for autonomously driving the vehicle [claim 1]).
MEUTER further discloses that uncompressed data cubes may be used, and a ML (machine learning) based bin suppression method may be utilized [0082]; and all beamvectors below CFAR (constant false alarm rate) level may be suppressed [0082]. In a same or similar field of endeavor, EVANS teaches that the machine learning model may include a range-doppler bin estimation neural network, and the method may evaluate the one or more first range-doppler maps by evaluating the one or more first range-doppler maps and the second range-doppler map with the range-doppler bin estimating neural network to generate range and doppler bins corresponding to the range and velocity of a respective object of the one or more objects. The method of this may also include identifying phase and magnitude components of the range-doppler bin corresponding to the range and the velocity of the respective object [0010].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of EVANS, because doing so would improve reliability and success of object detection, as recognized by EVANS.
Regarding claim 7, MEUTER, as modified, discloses the method of claim 1,
In a same or similar field of endeavor, EVANS teaches that the machine learning model may include both an azimuth angle regression neural network and an elevation regression neural network [0057].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of EVANS, because doing so would improve reliability and accuracy of object detection, as recognized by EVANS.
Regarding claim 9, MEUTER/ EVANS discloses the method of claim 1, wherein the at least one beam vector list corresponds to a number of cells in a range-Doppler map (a stack of data for a fixed range and a fixed range rate, including data for various antennas, may be referred to as a beam vector 1408 (which may also be referred to as a data cube) [MEUTER 0144]); (evaluate the one or more first range-doppler maps by evaluating the one or more first range-doppler maps and the second range-doppler map with the range-doppler bin estimating neural network to generate range and doppler bins corresponding to the range and velocity of a respective object of the one or more objects [EVANS 0010], cited and incorporated in the rejection of claim 1).
Regarding claim 11, MEUTER/ EVANS discloses the method of claim 1, wherein the neural network is trained end-to-end (the network may be trained to output various types of spectra at output which simplifies integration into other networks such as an end-2-end network [MEUTER 0115]).
Regarding claim 12, MEUTER/ EVANS discloses the method of claim 1, further comprising the following step carried out by computer hardware components: transmitting the at least one beam vector list to another neural network (as an input, a 3D Compressed Data Cube (CDC) 112 may be used. This cube may be sparse as all beamvectors below CFAR (constant false alarm rate) level may be suppressed [MEUTER 0082]); (data from the CDC domain 118 may be used in a CDC domain subnet 126. In the CDC domain subnet 126, on each beamvector of the range Doppler map, an angle finding network is applied. This network may be an MLP (multilayer perceptron). The CDC domain subnetwork 126 may create a range, angle, Doppler cube which may be subsequently processed with convolution layers to filter the input [MEUTER 0083]).
Regarding claim 13, MEUTER/ EVANS discloses a computer system comprising a plurality of computer hardware components configured to carry out steps of the computer implemented method of claim 1 (a computer system 900 with a plurality of computer hardware components configured to carry out steps of a computer implemented method for object detection [MEUTER 0136]).
Regarding claim 14, MEUTER/ EVANS discloses a vehicle, comprising the computer system of claim 13 and the at least one radar sensor (a vehicle comprises the computer system and the radar sensor [MEUTER 0208]).
Regarding claim 15, MEUTER/ EVANS discloses a non-transitory computer readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the computer implemented method of claim 1 (a non-transitory computer readable medium comprises instructions for carrying out the computer implemented method [MEUTER 0209]).
Regarding claim 16, MEUTER/ EVANS discloses the method of claim 1, wherein the at least one object detected in the environment of the vehicle is a vulnerable road user including one of a cyclist or a pedestrian (a deep neural network (NN) architecture 1308 may provide processing, fusion and/or tracking, in order to obtain object tracks bounding boxes 1310, pedestrian tracks bounding boxes 1312, and/or a semantic segmentation map or guardrail segmentation 1314 [MEUTER 0141], cited and incorporated in the rejection of claim 1).
Regarding claim 17, MEUTER/ EVANS discloses the method of claim 1, wherein performing object detection includes performing at least one of pedestrian detection or pole detection (a deep neural network (NN) architecture 1308 may provide processing, fusion and/or tracking, in order to obtain object tracks bounding boxes 1310, pedestrian tracks bounding boxes 1312, and/or a semantic segmentation map or guardrail segmentation 1314 [MEUTER 0141], cited and incorporated in the rejection of claim 1).
Claim(s) 2 and 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over MEUTER, in view of EVANS, and further in view of Westra et al. (US 2022/0252716 A1 newly cited “WESTRA”).
Regarding claim 2, MEUTER/ EVANS discloses the method of claim 1,
In a same or similar field of endeavor, WESTRA teaches that each matrix cell/bin holds an intensity value corresponding to the energy of returned radar wave signals detected for a certain range cell and a certain radial velocity range given by the position of the matrix cell/bin within the range-Doppler matrix [0018]. Selecting a hit range cell or a number of neighboring hit range cells is performed after generation of the range-Doppler matrices, and comprises selecting the range cell column holding the highest summation of intensity values when summed for all velocity cells/bins from the group of range cells that represent the object that is to be classified [0050]. A three-dimensional data array based on three cropped range-Doppler matrices, with data from the three-dimensional data array being input to a convolutional neural network for further processing [0086].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of WESTRA, because doing so would optimize the processing of the obtained reflected data to perform a successful classification of an object, as recognized by WESTRA.
Regarding claim 5, MEUTER/ EVANS discloses the method of claim 1,
In a same or similar field of endeavor, WESTRA teaches that each matrix cell/bin holds an intensity value corresponding to the energy of returned radar wave signals detected for a certain range cell and a certain radial velocity range given by the position of the matrix cell/bin within the range-Doppler matrix [0018]. Selecting a hit range cell or a number of neighboring hit range cells is performed after generation of the range-Doppler matrices, and comprises selecting the range cell column holding the highest summation of intensity values when summed for all velocity cells/bins from the group of range cells that represent the object that is to be classified [0050]. A three-dimensional data array based on three cropped range-Doppler matrices, with data from the three-dimensional data array being input to a convolutional neural network for further processing [0086].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of WESTRA, because doing so would optimize the processing of the obtained reflected data to perform a successful classification of an object, as recognized by WESTRA.
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over MEUTER, in view of EVANS, and further in view of Sick et al. (US 2019/0279366 A1 newly cited “SICK”).
Regarding claim 3, MEUTER/ EVANS discloses the method of claim 1,
In a same or similar field of endeavor, SICK teaches that the direction from which the interference signal arrives is determined for each value of the distance/speed distribution, i.e. for each point on the range-Doppler map. All of the information in the range-Doppler map is exploited. This results in a four dimensional data range, comprising the following dimensions: distance r, speed v, azimuth angle and elevation angle [0049]. The application system contains a trained artificial neural network, and outputs the segmentation. The application system uses distance, speed, azimuth angle and elevation angle as the input channels [0064]. The artificial neural network is thus configured to translate the radar data, distance, speed, azimuth angle and elevation angle into object data [0049].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of SICK, because doing so would utilize all the detected parameters and improve target detection and accuracy, as recognized by SICK.
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over MEUTER, in view of EVANS, and SICK, and further in view of Schoor (US 2021/0364626 A1 newly cited “SCHOOR”).
Regarding claim 4, MEUTER/ EVANS/ SICK discloses the method of claim 3,
In a same or similar field of endeavor, SCHOOR teaches that the control and evaluation unit is designed to subject the received signals to a discrete Fourier transform, the control and evaluation unit being designed, in the aforementioned operating mode for the respective evaluation channels, to calculate spectral components for the selected distances or frequency positions during the discrete Fourier transform and to evaluate the estimation of the angle [0025].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of SCHOOR, because doing so would improve accuracy and efficiency of angle estimation, as recognized by SCHOOR.
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over MEUTER, in view of EVANS, and WESTRA, and further in view of Fetterman et al. (US 2017/0059695 A1 previously cited “FETTERMAN”).
Regarding claim 6, MEUTER/ EVANS/ WESTRA discloses the method of claim 5,
In a same or similar field of endeavor, FETTERMAN teaches averaging of multiple range-Doppler maps for the region being monitored [0044].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of FETTERMAN, because doing so would result in improved signal-to-noise ratio (SNR), as recognized by FETTERMAN. In addition, both of the prior art references, MEUTER and FETTERMAN, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, radar processing for target detection.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over MEUTER, in view of EVANS, and further in view of Nunn et al. (US 2019/0325241 A1 previously cited “NUNN”).
Regarding claim 8, MEUTER/ EVANS discloses the method of claim 1,
In a same or similar field of endeavor, NUNN teaches that it can be that the convolution result is added to a constant and that an activation function is applied, which can be a function configured to perform a transformation to a predefined scale. Examples for activation functions are the sigmoid function and the tanh function [0040].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of NUNN, because doing so would be powerful in robustly extracting reliable dynamic information and easily be integrated into many applications such as an autonomous driving application, as recognized by NUNN. In addition, both of the prior art references, MEUTER and NUNN, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, extraction of radar data using a neural network.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over MEUTER, in view of EVANS, and further in view of Schubert et al. (US 2021/0116541 A1 previously cited “SCHUBERT”).
Regarding claim 10, MEUTER/ EVANS discloses the method of claim 9,
In a same or similar field of endeavor, SCHUBERT teaches that a range-Doppler matrix M may be generated by the radar system. A partial quantity of the cells of range-Doppler matrix M is selected in a selection device 11. To that end, for example, a predetermined number of cells of range-Doppler matrix M may be selected randomly. For instance, a maximum of 1% or even less, e.g., 5 per thousand, 2 per thousand, 1 per thousand or possibly even fewer of the cells of range-Doppler matrix M may be selected [0041].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of MEUTER to include the teachings of SCHUBERT, because doing so would simplify the determination of the detection and efficiently improve ascertainment of the detection, as recognized by SCHUBERT. In addition, both of the prior art references, MEUTER and SCHUBERT, teach features that are directed to analogous art and they are directed to the same field of endeavor, that is, processing of a range-Doppler map in a radar system.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Bharadwaj, Jr. et al. (US 2019/0391251 A1 newly cited) is cited as pertinent art for the disclosure overall, and in particular the details of the confidence metric being based on at least one of: strength of signals received by at least two receiver antennas; a distribution of FFT output samples as a function of range and Doppler [0028]. A neural network classifier is used to provide a confidence metric for at least one object parameter [0021]. Confidence metrics provided by the ANN classifier operations 520 can be used to determine the amount of increase or decrease in the CFAR threshold [0036].
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HAILEY R LE whose telephone number is (571)272-4910. The examiner can normally be reached 9:00 AM - 5:00 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, VLADIMIR MAGLOIRE can be reached at (571) 270-5144. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Hailey R Le/Examiner, Art Unit 3648 September 11, 2026
Prosecution Insights