DETAILED ACTION
This action is in response to the application filed on January 21st, 2025. Claims 1-12 are pending and have been examined.
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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on January 21st, 2025 is being considered by the examiner.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the reference sign 1600 mentioned in page 12 of the description “Finally the method 100 may include detecting 1600 objects based on the determined first features and/or second features”. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claim 1 is objected to because of the following informalities:
Claim 1, line 10: “parse spectra” contains a minor typographical error, this should read “sparse spectra”
Appropriate correction is required.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim 1-2, 5, 7-8, 10-11, and 12 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by “Deep Learning-based Object Classification on Automotive Radar Spectra” (herein after referred to by its primary author, Patel).
In regards to claim 1, Patel teaches a method for sensing an environment of a device using sparse spectra, the method comprising the following steps: generating, with a sensor of the device, a time signal with information about features of one or more objects in the environment of the device (Patel Section II A “A radar sensor is mounted on the front bumper of the test vehicle which drives between different objects on a test track, approaching them from several different directions.”); determining dense spectra having N dimensions based on the time signal, wherein the time signal includes information for generating dense spectra having K dimensions, wherein K is greater than or equal to N (Patel Section II B “In this study we are mainly interested in the range-azimuth spectrum, therefore we take the velocity slice which contains the maximum intensity in the 3D ROI which results in a 2D ROI containing 64 range and 66 azimuth bins. See Fig. 1 for examples of ROIs from the range-azimuth spectrum.” Examiner note: This section teaches that only 2 dimensions range and azimuth are only considered for this reference and the 3rd dimension of velocity is ignored by choosing 1 slice with a constant velocity.); determining parse spectra having N dimensions based on the dense spectra having N dimensions, wherein an amount of data for representing the sparse spectra is less than an amount of data for representing the dense spectra having N dimensions (Patel Section II B “For each detected object, we cut out a region-of-interest (ROI) of the 3D-spectrum with the range, velocity and azimuth extent of 5m, 0.7m/s, and 0.5 rad1, respectively, where the highest detected peak of the object is in the center of the ROI.” Examiner note: Only the data within the ROIs are considered. These ROIs can be considered sparse spectra, as they contains less data as compared to the full spectra the ROIs were taken from); and determining first features of the one or more objects for one or more points in the sparse spectra (Patel Figure 2 Examiner note: The CNN extracts features through convolutional layers.).
In regards to claim 2, Patel teaches the method according to claim 1, the method further comprising: selecting the one or more points in the sparse spectra (Patel Figure 2 Examiner note: The convolutional layer performs convolutions on a sliding window for each point in the ROI).
In regards to claim 5, Patel teaches the method according to claim 2, wherein K is greater than N (Patel Section II B “In this study we are mainly interested in the range-azimuth spectrum, therefore we take the velocity slice which contains the maximum intensity in the 3D ROI which results in a 2D ROI containing 64 range and 66 azimuth bins. See Fig. 1 for examples of ROIs from the range-azimuth spectrum.” Examiner note: In this section, K is equal to 3 and N is equal to 2).
In regards to claim 7, Patel teaches the method according to claim 1, wherein the determining of the sparse spectra having N dimensions based on the dense spectra having N dimensions includes disregarding data outside a respective range around a point or a local maximum (Patel Section II B “For each detected object, we cut out a region-of-interest (ROI) of the 3D-spectrum with the range, velocity and azimuth extent of 5m, 0.7m/s, and 0.5 rad1, respectively, where the highest detected peak of the object is in the center of the ROI.”).
In regards to claim 8, Patel teaches the method according to claim 7, wherein a respective area around the point or the local maximum is an N-dimensional rectangle, or an N-dimensional sphere, or an N-dimensional ellipsoid (Patel Figure 2 Examiner note: The input to this CNN is the ROI previously extracted in claim 7, this ROI is an N-dimensional rectangle as can be seen from the figure).
In regards to claim 10, Patel teaches The method according to claim 1, wherein: (i) the sensor of the device is a RADAR sensor, or a LIDAR sensor, or a SONAR sensor, or an ultrasonic sensor, and/or (ii) N is equal to 2 having dimensions of distance and speed (Patel Section II A “A radar sensor is mounted on the front bumper of the test vehicle which drives between different objects on a test track, approaching them from several different directions.”).
In regards to claim 11, Patel anticipates the claim limitations as in the consideration of claim 1.
In regards to claim 12, Patel anticipates the claim limitations as in the consideration of claim 1.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 3-4 are rejected under 35 U.S.C. 103 as being unpatentable over Patel in view of “Graph Convolutional Networks for 3D Object Detection on Radar Data” (herein after referred to by its primary author, Meyer).
In regards to claim 3, Patel teaches the method according to claim 1 but fails to teach wherein determining of the first features of the one or more objects for one or more points in the sparse spectra further includes determining second features of the object from the dense spectra having K dimensions without the dense spectra having N dimensions according to the one or more points.
However, Meyer teaches wherein determining of the first features of the one or more objects for one or more points in the sparse spectra further includes determining second features of the object from the dense spectra having K dimensions without the dense spectra having N dimensions according to the one or more points (Meyer Abstract “In this work, we focus on fully leveraging raw radar tensor data instead of building up on human-biased point clouds which are the typical result of traditional radar signal processing techniques.”; Figure 1; Figure 1 Description “Detections of one test frame overlayed on the radar tensor data. Here the detections are only visualized in 2D but they are actually 3D boxes.”; Figure 3 Examiner note: This reference teaches detecting objects from raw RADAR tensor data (analogous to dense spectra with 3 dimensions, as can be seen in “Radar Tensor” of figure 3) by inputting the radar tensor into multiple neural networks to create 3D bounding boxes of objects, as seen in figure 3 “3D Bounding Boxes”. This is analogous to using the dense spectra having K dimensions to determine features of the objects).
Meyer is considered to be analogous to the claimed invention because they are both in the same field of object detection from RADAR data. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the system of Patel to include the teachings of Meyer, to provide the advantage of a robust system (Meyer Abstract “In this work, we focus on fully leveraging raw radar tensor data instead of building up on human-biased point clouds which are the typical result of traditional radar signal processing techniques.”; Section 1 “Therefore, using radar data for object detection additionally, can improve both redundancy and robustness in the overall autonomous driving stack.”)
In regards to claim 4, Patel in view of Meyer teaches the method according to claim 3 wherein the method further comprises: detecting the one or more objects in the environment of the device based on the first features (Patel Figure 2); and/or detecting the one or more objects in the environment of the device based on the second features (Meyer Figure 3); and/or classifying the one or more objects in the environment of the device (Patel Figure 2); and/or semantic segmentation of the first features and/or the second features and/or the dense spectra and/or the sparse spectra; and/or; estimating a free space in the environment of the device (Meyer Figure 4 Examiner note: This figure shows that objects are detected and given 3D bounding boxes in a scene. These objects can be considered “non-free space”, and by detecting the non-free space, the remaining area would be considered free space).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Patel in view of “Fast Two-Dimensional CFAR Procedure” (herein after referred to by its primary author, Kronauge).
In regards to claim 6, Patel teaches the method according to claim 1, including the determining of the sparse spectra having N dimensions based on the dense spectra having N dimensions.
Patel fails to teach wherein the determining of the sparse spectra having N dimensions based on the dense spectra having N dimensions includes disregarding data that are less than a threshold value.
However, Kronauge teaches wherein the determining of the sparse spectra having N dimensions based on the dense spectra having N dimensions includes disregarding data that are less than a threshold value (Kronauge Figure 2 “Detection Y > T”; Section II “The random variable inside the test cell is always denoted by Y and the calculated threshold is described by the parameter T.”; Equation (5) Examiner note: This section shows that a given cell Y is determine to be noise (not a target) if the value is less than a threshold T. This leads to spectra with less data, as any noisy cells are filtered out for the target list).
Kronauge is considered to be analogous to the claimed invention because they are both in the same field of RADAR processing for depth/range recovery. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the system of Patel to include the teachings of Kronauge, to provide the advantage of a fast adaptive system which estimates the noise level in radar spectra (Kronauge Section II “To develop a fast, adaptive, and reliable procedure to estimate the average noise power in a multitarget environment based on the random variables inside the two dimensional RDM is a technical challenge. In this context the design of the two-dimensional reference window is already a very important task in real applications.”)
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Patel in view of “Maritime Radar Target Detection Using Convolutional Neural Networks” (herein after referred to by its primary author, Williams).
In regards to claim 9, Patel teaches the method according to claim 1 but fails to teach wherein determining sparse spectra having N dimensions occurs using a neural network.
However, Williams teaches wherein determining sparse spectra having N dimensions occurs using a neural network (Williams Figure 2; Section III A “After the convolutional block, the data is downsampled to 16 × 16, then 8 ×8 and finally 4 × 4, followed by mirrored upsampling stages as described above.” Examiner note: This section teaches that the input radar spectra is downsampled to a lower size, this is analogous to creating sparse spectra from dense spectra, as the amount of data used to represent the spectra is reduced).
Williams is considered to be analogous to the claimed invention because they are both in the same field of RADAR processing for depth/range recovery. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the system of Patel to include the teachings of Williams, to provide the advantage of a non-blurred output after reducing the spectra’s data (Williams Section III “CNNs generally use a series of convolution and downsampling layers to aggregate local feature responses from different locations. Our model, like autoencoders or semantic segmentation models, needs to convert this information back to the original image scale by a corresponding set of up sampling operations. The downsampling part of the network is called an ‘encoder’ and the upsampling part is called a ‘decoder’. Naive upsampling alone will lead to a blurred result.”)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
“Deep-Neural-Network-Enabled Vehicle Detection Using High-Resolution Automotive Radar Imaging” teaches a method of detecting vehicles using RADAR imaging.
“3-D Object Detection for Multiframe 4-D Automotive Millimeter-Wave Radar Point Cloud” teaches a method of using LIDAR and RADAR data to detection objects near a vehicle.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CALEB LOGAN ESQUINO whose telephone number is (703)756-1462. The examiner can normally be reached M-Fr 8:00AM-4:00PM 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, Andrew Bee can be reached at (571) 270-5183. 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.
/CALEB L ESQUINO/ Examiner, Art Unit 2677
/ANDREW W BEE/ Supervisory Patent Examiner, Art Unit 2677
Prosecution Insights