DETAILED ACTION
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 .
Response to Amendment
The amendment filed 01/12/2026 has been entered.
Claims 1-3, and 9-11 are amended.
Claims 1-11 are pending.
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.
Claims 1-5, 7 and 9-11 are rejected under 35 U.S.C. 103 as being unpatentable over Kirsch (US 20210088641 A1) in view of Wang (US 20230031733 A1).
Regarding claim 1, Kirsch teaches transmitting using at least one ultrasonic sensor, toward an object[Fig 1 has ultrasonic sensor #104];
receiving from the object and using the at least one ultrasonic sensor, a second signal that is a backscattered echo of the first ultrasonic signal [Fig 1 shows sensor #104 transmitting and receiving signals #110 from object];
processing the second signal into a digital signal that represents samples from a sampled time-domain waveform of the backscattered echo[0057 has control device extracting features meaning it is sampling the echo; 0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals], each of the samples corresponding to a respective amplitude value of the backscattered echo at successive time instants; [Sensor data #116 being sent for processing via wire; 0034 and 0037 show echoes have amplitude; 0066 has processing to extract amplitude];
extracting from the digital signal a selected signal a portion corresponding to a continuous time interval for representing an echo event of the backscattered signal[0042, 0071 and claim 5 have defined time intervals], the time interval being a time-limited time segment from within a time period represented by the digital signal[0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals];…..
feeding the ….. vector into a neural network an input variable[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075];
and determining object class information for the object using the neural network, wherein, based on the input variable, the neural network produces an output variable which indicates a probability value for at least one defined object class for the object.[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075]
Kirsch does not explicitly teach the feature vector is two dimensional[Though selection of number of dimensions in a feature vector would have been a matter of design choice for a person of ordinary skill in the art]
Wang teaches transforming the selected signal portion into a two-dimensional time-frequency vector that[0022, 0028 has input data being two dimensional time frequency vector], for each of a plurality of successive time intervals of the selected signal portion, specifies a frequency spectrum of the backscattered echo including magnitudes of frequency components present within the respective time interval; [0018 has predetermined sampling frequency and time frame lengths]
feeding the two-dimensional time-frequency vector into a neural network as an input variable [Abstract; 0022 has time-frequency vector being used as input for classifier];
It would have been obvious to one of ordinary skill in the art before the filing date to have modified the ultrasonic sensor method in Kirsch with the time-frequency vector as input of Wang in order to complement the values and optimize the number of dimensions in the feature vector.
Regarding claim 9, Kirsch teaches transmit a first signal toward an object[Fig 1 has ultrasonic sensor #104];
receive from the object a second signal, that is a backscattered echo of the first ultrasonic signal [Fig 1 shows sensor #104 transmitting and receiving signals #110 from object];
process the second signal into a digital signal that represents samples from a sampled time-domain waveform of the backscattered echo[0057 has control device extracting features meaning it is sampling the echo; 0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals], each of the samples corresponding to a respective amplitude value of the backscattered echo at successive time instants; [Sensor data #116 being sent for processing via wire; 0034 and 0037 show echoes have amplitude; 0066 has processing to extract amplitude];
extract from the digital signal a selected signal portion corresponding to a continuous time interval for representing an echo event of the backscattered signal[0042, 0071 and claim 5 have defined time intervals], the time interval being a time-limited time segment from within a time period represented by the digital signal[0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals];…..
feed the ….. vector into a neural network an input variable[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075];
and determine object class information for the object using the neural network, wherein, based on the input variable, the neural network produces an output variable which indicates a probability value for at least defined object class for the object.[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075]
Kirsch does not explicitly teach the feature vector is two dimensional[Though selection of number of dimensions in a feature vector would have been a matter of design choice for a person of ordinary skill in the art]
Wang teaches transform the selected signal portion into a two-dimensional time-frequency vector that[0022, 0028 has input data being two dimensional time frequency vector], for each of a plurality of successive time intervals of the selected signal portion, specifies a frequency spectrum of the backscattered echo including magnitudes of frequency components present within the respective time interval; [0018 has predetermined sampling frequency and time frame lengths]
feed the two-dimensional time-frequency vector into a neural network as an input variable [Abstract; 0022 has time-frequency vector being used as input for classifier];
It would have been obvious to one of ordinary skill in the art before the filing date to have modified the ultrasonic sensor method in Kirsch with the time-frequency vector as input of Wang in order to complement the values and optimize the number of dimensions in the feature vector.
Regarding claim 10, Kirsch teaches transmitting using the at least one ultrasonic sensor, a first ultrasonic signal toward an object[Fig 1 has ultrasonic sensor #104];
receiving from the object and using the at least one ultrasonic sensor, a second signal that is a backscattered echo of the first ultrasonic signal [Fig 1 shows sensor #104 transmitting and receiving signals #110 from object];
processing the second signal into a digital signal that represents samples from a sampled time-domain waveform of the backscattered echo[0057 has control device extracting features meaning it is sampling the echo; 0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals], each of the samples corresponding to a respective amplitude value of the backscattered echo at successive time instants; [Sensor data #116 being sent for processing via wire; 0034 and 0037 show echoes have amplitude; 0066 has processing to extract amplitude];
extracting from the digital signal a selected signal portion corresponding to a continuous time interval for representing an echo event of the backscattered signal[0042, 0071 and claim 5 have defined time intervals], the time interval being a time-limited time segment from within a time period represented by the digital signal[0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals];…..
feeding the ….. vector into a neural network an input variable[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075];
and determining object class information for the object using the neural network, wherein, based on the input variable, the neural network produces an output variable which indicates a probability value for at least defined object class for the object.[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075]
Kirsch does not explicitly teach the feature vector is two dimensional[Though selection of number of dimensions in a feature vector would have been a matter of design choice for a person of ordinary skill in the art]
Wang teaches transforming the selected signal portion into a two-dimensional time-frequency vector that[0022, 0028 has input data being two dimensional time frequency vector], for each of a plurality of successive time intervals of the selected signal portion, specifies a frequency spectrum of the backscattered echo including magnitudes of frequency components present within the respective time interval; [0018 has predetermined sampling frequency and time frame lengths]
feeding the two-dimensional time-frequency vector into a neural network as an input variable [Abstract; 0022 has time-frequency vector being used as input for classifier];
It would have been obvious to one of ordinary skill in the art before the filing date to have modified the ultrasonic sensor method in Kirsch with the time-frequency vector as input of Wang in order to complement the values and optimize the number of dimensions in the feature vector.
Regarding claim 11, Kirsch teaches transmit, using at least one ultrasonic sensor a first signal toward an object[Fig 1 has ultrasonic sensor #104];
receive from the object and using the at least one ultrasonic sensor, a second signal that is a backscattered echo of the first ultrasonic signal from the object[Fig 1 shows sensor #104 transmitting and receiving signals #110 from object];
process the second signal into a digital signal that represents samples from a sampled time-domain waveform of the backscattered echo[0057 has control device extracting features meaning it is sampling the echo; 0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals], each of the samples corresponding to a respective amplitude value of the backscattered echo at successive time instants; [Sensor data #116 being sent for processing via wire; 0034 and 0037 show echoes have amplitude; 0066 has processing to extract amplitude];
extract from the digital signal a selected signal portion corresponding to a continuous time interval for representing an echo event of the backscattered signal[0042, 0071 and claim 5 have defined time intervals], the time interval being a time-limited time segment from within a time period represented by the digital signal[0034 and 0042 has echo having transit time and extraction at time intervals meaning echo data is in the time domain; 0071 has data as function of time; See also claim 5 for classification at time intervals];…..
feed the ….. vector into a neural network an input variable[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075];
and determine object class information for the object using the neural network, wherein, based on the input variable, the neural network produces an output variable which indicates a probability value for at least defined object class for the object.[0057 has features used as input data for neural network for object classification. See also 0027-0031 and 0075]
Kirsch does not explicitly teach the feature vector is two dimensional[Though selection of number of dimensions in a feature vector would have been a matter of design choice for a person of ordinary skill in the art]
Wang teaches transform the selected signal portion into a two-dimensional time-frequency vector that[0022, 0028 has input data being two dimensional time frequency vector], for each of a plurality of successive time intervals of the selected signal portion, specifies a frequency spectrum of the backscattered echo including magnitudes of frequency components present within the respective time interval; [0018 has predetermined sampling frequency and time frame lengths]
feed the two-dimensional time-frequency vector into a neural network as an input variable [Abstract; 0022 has time-frequency vector being used as input for classifier];
It would have been obvious to one of ordinary skill in the art before the filing date to have modified the ultrasonic sensor method in Kirsch with the time-frequency vector as input of Wang in order to complement the values and optimize the number of dimensions in the feature vector.
Regarding claim 2, Kirsch, as modified, teaches that further comprising feeding at least one second input variable into the neural network, wherein the second input variable includes distance formation which represents a distance between the at least one ultrasonic sensor and the one object. [0021, 0066 has distance used as input]
Regarding claim 3, Kirsch, as modified, teaches that he neural network includes a plurality of fully connected layers, spanning from an anterior end of the neural network to a posterior end of the neural network, [0031 has multiple layers in the classifier/neural netowrk]and the distance information is fed as an intermediate feed into a posterior classifier layer portion of the fully connected layers of the neural network that is downstream of an input layer at the anterior end, such that the neural network completes a single classification process begun with input provided to input layer using the distance information fed into the posterior classifier layer.[ 0021, 0066 has distance used as input and 0031 has multilayer and neural network; Fig 2 has object information # 118 being further processed from classifier #204 back to evaluation #200 at 0063 meaning its intermediate feed]
Wang also teaches a multilayer neural network with intermediate feed of data[Abstract, 0003, 0022]
Regarding claim 4, Kirsch does not explicitly teach wherein the neural network includes at least one first convolutional layer with a non-square filter kernel, a narrow side of which extends along a time dimension of the feature vector, and a second convolutional layer with a non-square filter kernel, a narrow side of which extends along a frequency dimension of the feature vector.
Wang teaches wherein the neural network includes at least one first convolutional layer with a non-square filter kernel, a narrow side of which extends along a time dimension of the feature vector, and a second convolutional layer with a non-square filter kernel, a narrow side of which extends along a frequency dimension of the feature vector. [Abstract, 0003, 0021-0025 multi dimensional feature vectors from the data including time and frequency]
It would have been obvious to one of ordinary skill in the art before the filing date to have modified the ultrasonic sensor method in Kirsch with the two dimensional feature vector with time and frequency as input of Wamg in order to complement the values and optimize the number of dimensions in the feature vector.
Regarding claim 5, Kirsch, as modified, teaches that wherein the selected signal portion from the digital signal represents a fixed time period from an ascertained starting point of the digital signal. [0042 has defined time intervals for sensor received data]
Regarding claim 7, Kirsch, as modified, teaches that wherein the step of processing the second signal into a digital signal includes filtering the digital signal to improve an S/N ratio. [0063, 0066 has filtering/masking of noise].
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Kirsch (US 20210088641 A1) in view of Wang (US 20230031733 A1) as applied to claim 1 above, and further in view of Palanisamy (US 11016495 B2).
Regarding claim 6, Kirsch does not explicitly teach wherein the selected signal portion is ascertained from the digital signal using a sliding window approach or a pulse-echo method, wherein a window which is shorter than an entire recording length of the digital signal is shifted over the entire recording length of the digital signal.
Palanisamy teaches that wherein the selected signal portion is ascertained from the digital signal using a sliding window approach or a pulse-echo method, wherein a window which is shorter than an entire recording length of the digital signal is shifted over the entire recording length of the digital signal. [Col 17 Lines 50-65 have sliding window for sensor data].
It would have been obvious to one of ordinary skill in the art before the filing date to have modified the ultrasonic sensor method in Kirsch with use of sliding windows in Palanisamy in order to change the time taken for the system to process data.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Kirsch (US 20210088641 A1) in view of Wang (US 20230031733 A1) as applied to claim 1 above, and further in view of Kreib (US 12013477 B2 ).
Regarding claim 8, Kirsch docs not explicitly teach wherein the second signal is configured as an analog signal.
Kreib teaches wherein the second signal is configured as an analog signal. [Col 9, Lines 5-10 and Col 10 , Lines 20-25 have digital and analog signals]
It would have been obvious to one of ordinary skill in the art before the filing date to have modified the ultrasonic sensor method in Kirsch with the use of analog and digital signals for feature vector input of Kreib in order to increase feature vector dimensionality to have more data.
Response to Arguments
Applicant's arguments filed 01/12/2026 have been fully considered but they are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Regarding applicant’s arguments on remarks pages 8-12 against the prior art, applicant is reading the prior art overly narrowly and in response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Specifically an echo waveform is by default a time domain waveform of various amplitudes and selecting any section would be selecting an echo event as pointed out in the present rejection above.
Regarding the argument concerning windowing of claim 6, applicant is also interpreting the prior art overly narrowly and, it is pointed out that managing an input history means that there is extracting a time limited signal.
Applicant's remaining arguments amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. Rejections are maintained – and no allowable subject matter can be identified at this time.
Conclusion
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 VIKAS NMN ATMAKURI whose telephone number is (571)272-5080. The examiner can normally be reached Monday-Friday 7:30am-5:30pm.
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, Isam Alsomiri can be reached at (571)272-6970. 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.
/VIKAS ATMAKURI/Examiner, Art Unit 3645
/HELAL A ALGAHAIM/SPE , Art Unit 3645