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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/22/2025 has been entered.
Election/Restrictions
Applicant's election with traverse of Invention I in the reply filed on 8/6/2025 is acknowledged. The traversal is on the ground(s) that the three identified subcombinations are not distinct. This is not found persuasive because the claim language contradicts the assertion. Group II includes a doppler signature and Group I includes a random forest classifier. These are distinct. They are, however, intended to be used together, while they do not overlap in scope.
The requirement is still deemed proper and is therefore made FINAL.
Claims 9-13 and 15-20 are withdrawn from further consideration pursuant to 37 CFR 1.142(b), as being drawn to a nonelected inventions, there being no allowable generic or linking claim. Applicant timely traversed the restriction (election) requirement in the reply filed on 8/6/2025.
Dependent claims requiring the limitations of an allowable base, generic claim shall be rejoined.
Claim Rejections - 35 USC § 103
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, 3-8, 14, 21 are rejected under 35 U.S.C. 103 as being unpatentable over Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) in view of Berntorp (US PG Publication 2018/0284785 A1) and Kaniyala (US PG Publication US 2023/0033533 A1).
Regarding Claim 1, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses a system, comprising:
a memory; and at least one computing device in communication with the memory, the at least one computing device (software, Author contributions, p. 12) being configured to:
receive data (the angle, speed, height and distance threat factors that can reflect the target’s dynamic threat capability, p. 3) describing a plurality of tracks (target space status information, p. 3) individually corresponding to one of a plurality of identified objects (UAV swarm, p. 3) from a radar system (radar p. 2) corresponding to a particular airspace (our defense position, p. 3), wherein the data describing the plurality of tracks comprises machine-learning metadata (angle, speed, height, distance, type, p. 3);
generate a plurality of sets of prioritization scores (parameters Sv, Sa, Sh, SR, Sc, p. 3-6, ##1-6, eqs. 1-6) individually corresponding to the plurality of tracks (target, p. 3-6; m air raid targets, p. 7);
by generating a first set of prioritization scores (e.g., parameter Sv, p. 3-6, ##1-6, eqs. 1-6, for the m air raid targets, p. 7) of the plurality of sets of prioritization scores (parameters Sv, Sa, Sh, SR, Sc, p. 3-6, ##1-6, eqs. 1-6) by applying a first [] model (eq. 1, p. 3-6, ##1-6) of the plurality of different [] algorithms (eqs. 1-6, p. 3-6, ##1-6) to the data describing the plurality of tracks (target, p. 3-6; m air raid targets, p. 7); and
generating a second set of prioritization scores (parameter Sh, p. 3-6, ##1-6, eqs. 1-6, for the m air raid targets, p. 7) of the plurality of sets of prioritization scores (parameters Sv, Sa, Sh, SR, Sc, p. 3-6, ##1-6, eqs. 1-6) by applying a second [] model (eq. 3, p. 3-6, ##1-6) of the plurality of different [] algorithms (eqs. 1-6, p. 3-6, ##1-6) to the data describing (target detection and tracking by radar and infrared, p. 9) the plurality of tracks (target, p. 3-6; m air raid targets, p. 7), wherein each of the plurality of sets of prioritization scores is generated by a different one of the plurality of different [] algorithms (each of parameters Sv, Sa, Sh, SR, Sc, p. 3-6, ##1-6 is derived by one of eqs. 1-6);
generate a plurality of aggregate prioritization scores (threat degree F, p. 8) individually corresponding to the plurality of tracks (F vector: f1, f2, …, fn, p. 8, eq. 12, for the m air raid targets, p. 7; p. 10-11) based on the plurality of sets of prioritization scores (parameters Sv, Sa, Sh, SR, Sc, p. 3-6, ##1-6, eqs. 1-6);
and adjust a positioning (anti-swarm operation, p. 1) … based on the plurality of aggregate prioritization scores (threat value of each UAV, p. 1; F vector: f1, f2, …, fn, p. 8, eq. 12, for the m air raid targets, p. 7; p. 10-11).
Luo does not expressly disclose, but Berntorp (US PG Publication 2018/0284785 A1) teaches
train a plurality of different machine learning algorithms (train a random forest algorithm, which is based on deep decision trees, another embodiment trains a support vector machine, and a third embodiment trains a neural network [0109]) individually corresponding to a different type of machine learning algorithm (random forest, neural network, support vector [0109]);
generating … scores (level of risk, Fig. 1B) … by applying a first machine learning model (random forest) of the plurality of different machine learning algorithms (neural network, a support vector machine, and a deep decision tree, Claim 8);
generating … scores (level of risk, Fig. 1B) … by applying a second machine learning model (neural network) of the plurality of different machine learning algorithms (random forest, neural network, support vector [0109], Claims 7-8) to the data (the time-series signal, Claim 7)
each (classifying the time-series signal, Claims 7-8) … is generated by a different one of the plurality of different machine learning algorithms (one of the models is a deep decision tree—i.e., random forest, the other is neural network, Claims 7-8; [0109]).
Luo does not expressly disclose, but Kaniyala (US PG Publication US 2023/0033533 A1) teaches
adjust a positioning of at least one pan-tilt-zoom camera (the electronic device 102 may control panning of the imaging device 104 to change the angle of view of the imaging device 104 to … track a movement of the first player and the object [0031]).
One of ordinary skill in the art before the application was filed would have been motivated to replace the threat determination model of Luo with the threat determination models of Berntorp because Berntorp teaches that without assuming that the incoming vehicle wants to minimize risk, the model can process the possible trajectories and analyze the risk in real time [0050], improving the system by making it deployable and useful in time-critical applications.
One of ordinary skill in the art before the application was filed would have been motivated to supplement the defense system of Luo with the PTZ camera of Kaniyala because Kaniyala teaches that its system is effective for automating the tracking and response to rapid-movement events that require rapid decisions [0003], making it suitable for tracking objects in the joint radar/imaging threat tracking system of Luo.
Regarding Claim 3, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses the system of claim 1.
Luo does not expressly disclose, but Kaniyala (US PG Publication US 2023/0033533 A1) teaches wherein the plurality of different machine learning algorithms (logistic regression, naive bayes, K-Nearest Neighbors, decision trees, random forest, support vector machine, gradient descent, stochastic gradient descent, batch gradient descent, gradient boost, meta-heuristics [0060]) comprises at least one random forest classifier algorithm (random forest ML model [0038]).
One of ordinary skill in the art before the application was filed would have been motivated to supplement the defense system of Luo with the PTZ camera of Kaniyala because Kaniyala teaches that its system is effective for automating the tracking and response to rapid-movement events that require rapid decisions [0003], making it suitable for tracking objects in the joint radar/imaging threat tracking system of Luo.
Regarding Claim 4, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses the system of claim 1, wherein the at least one computing device is further configured to generate a particular aggregate prioritization score (e.g., f1 of the F vector, eq. 12) of the plurality of aggregate prioritization scores (F vector, eq. 12) as a weighted average (each row of the A matrix multiplied by the weight vector, eq. 12) of a particular set of prioritization scores (indicator vector for the n factors of the mth target, i.e., each row of the A matrix in eq. 12, p. 7) of the plurality of sets of prioritization scores (all rows of the A matrix in eq. 12).
Regarding Claim 5, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses the system of claim 1, wherein the at least one computing device is further configured to perform image analysis on at least one feed from the at least one camera to determine at least one respective type of at least one of the plurality of identified objects (imaging technology for feature extraction and target recognition, p. 3).
Luo does not expressly disclose, but Kaniyala (US PG Publication US 2023/0033533 A1) teaches PTZ camera (the electronic device 102 may control panning of the imaging device 104 to change the angle of view of the imaging device 104 to … track a movement of the first player and the object [0031]).
One of ordinary skill in the art before the application was filed would have been motivated to supplement the defense system of Luo with the PTZ camera of Kaniyala because Kaniyala teaches that its system is effective for automating the tracking and response to rapid-movement events that require rapid decisions [0003], making it suitable for tracking objects in the joint radar/imaging threat tracking system of Luo.
Regarding Claim 6, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses the system of claim 5.
Luo does not expressly disclose, but Kaniyala (US PG Publication US 2023/0033533 A1) teaches wherein the at least one computing device is further configured to render an updated user interface comprising at least one respective symbol corresponding to the at least respective type (assign a class label to the bounding box 510 [0060]).
One of ordinary skill in the art before the application was filed would have been motivated to supplement the defense system of Luo with the PTZ camera of Kaniyala because Kaniyala teaches that its system is effective for automating the tracking and response to rapid-movement events that require rapid decisions [0003], making it suitable for tracking objects in the joint radar/imaging threat tracking system of Luo.
Regarding Claim 7, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses the system of claim 1, wherein the data describing the plurality of tracks comprises machine-learning metadata corresponding to the radar system (dynamic attributes of target speed, entry angle, height and distance, p. 9).
Regarding Claim 8, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses a method, comprising:
receiving, via one of the one or more computing devices (software, Author contributions, p. 12), data describing a plurality of tracks (the angle, speed, height and distance threat factors that can reflect the target’s dynamic threat capability, p. 3) individually corresponding to one of a plurality of identified objects (UAV swarm, p. 3) from a radar system (radar p. 2) corresponding to a particular airspace (our defense position, p. 3);
generating, via one of the one or more computing devices, a plurality of sets of prioritization scores (parameters Sv, Sa, Sh, SR, Sc, p. 3-6, ##1-6, eqs. 1-6) individually corresponding to the plurality of tracks (target, p. 3-6; m air raid targets, p. 7), wherein each set of the plurality of sets of prioritization scores is generated by applying a different [] model (one of equations 1-6, p. 3-6, ##1-6, eqs. 1-6) of the plurality of different [] algorithms (all of equations 1-6, p. 3-6, ##1-6, eqs. 1-6) to the data describing (the angle, speed, height and distance threat factors that can reflect the target’s dynamic threat capability, p. 3; target detection and tracking by radar and infrared, p. 9) the plurality of tracks (target, p. 3-6; m air raid targets, p. 7);
generating, via one of the one or more computing devices, a plurality of aggregate prioritization scores (threat degree F, p. 8) individually corresponding to the plurality of tracks (F vector: f1, f2, …, fn, p. 8, eq. 12, for the m air raid targets, p. 7; p. 10-11) based on the plurality of sets of prioritization scores (parameters Sv, Sa, Sh, SR, Sc, p. 3-6, ##1-6, eqs. 1-6); and
adjusting, via one of the one or more computing devices, a positioning (anti-swarm operation, p. 1) … based on the plurality of aggregate prioritization scores (threat value of each UAV, p. 1; F vector: f1, f2, …, fn, p. 8, eq. 12, for the m air raid targets, p. 7; p. 10-11).
Luo does not expressly disclose, but Berntorp (US PG Publication 2018/0284785 A1) teaches training, via one of one or more computing devices (software [0119]), a plurality of different machine learning algorithms individually corresponding to a different type of machine learning algorithm (train a random forest algorithm, which is based on deep decision trees, another embodiment trains a support vector machine, and a third embodiment trains a neural network [0109]);
scores (level of risk, Fig. 1B, [0053], [0057], [0060], [0105], [0117]) is generated by applying a different machine learning model (classifying “intention” by training a random forest algorithm, which is based on deep decision trees, another embodiment trains a support vector machine, and a third embodiment trains a neural network [0109], Claims 7-8; By combining different combinations of driving intentions, slightly different trajectories are obtained [0065]; level of risk is determined by combination probability of the feasible trajectory to intersect and the be followed by a vehicle [0105]) of the plurality of different machine learning algorithms (random forest algorithm, which is based on deep decision trees, another embodiment trains a support vector machine, and a third embodiment trains a neural network [0109]).
Luo does not expressly disclose, but Kaniyala (US PG Publication US 2023/0033533 A1) teaches adjusting, via one of the one or more computing devices, a positioning of at least one pan-tilt-zoom (PTZ) camera (the electronic device 102 may control panning of the imaging device 104 to change the angle of view of the imaging device 104 to … track a movement of the first player and the object [0031]).
One of ordinary skill in the art before the application was filed would have been motivated to replace the threat determination model of Luo with the threat determination models of Berntorp because Berntorp teaches that without assuming that the incoming vehicle wants to minimize risk, the model can process the possible trajectories and analyze the risk in real time [0050], improving the system by making it deployable and useful in time-critical applications.
One of ordinary skill in the art before the application was filed would have been motivated to supplement the defense system of Luo with the PTZ camera of Kaniyala because Kaniyala teaches that its system is effective for automating the tracking and response to rapid-movement events that require rapid decisions [0003], making it suitable for tracking objects in the joint radar/imaging threat tracking system of Luo.
Regarding Claim 14, the claim is rejected on the grounds provided in Claim 1.
Regarding Claim 21, Luo (NPL “Threat Assessment Method of Low Altitude Slow Small Targets Based on Information Entropy and AHP,” Entropy 2021) discloses the system of claim 1, further comprising a PIR sensor, wherein the data describing the plurality of tracks comprises data from the PIR sensor (target detection and tracking by infrared, p. 9).
Response to Arguments
Applicant’s remarks filed 12/22/2025 have been considered but are not persuasive.
Applicant asserts that secondary reference Berntorp is silent on some claimed features. This argument is not persuasive because Berntorp is not relied upon to teach those features. As a result, Applicant’s arguments attack Berntorp individually where the rejection is based on a combination of references.
Applicant argues that Berntorp uses machine learning to detect “intention,” such as turning left or right; not determining “prioritization scores,” as claimed. Remarks at 8. This is not persuasive, as Berntorp determines a “level of risk,” a score analogous to prioritization scores, by applying the machine learning models that classify the intention (Berntorp at [0105]). The claim does not restrict how the machine learning model is applied to determine scores; Applicant can amend the claims to do so.
The prima facie case of obviousness does not require Berntorp to also teach the claim limitations disclosed by Luo, and therefore Applicant’s argument that Berntorp does not disclose “prioritization scores” is not persuasive.
Applicant argues that the different machine learning models of Berntorp are disclosed as different embodiments (Remarks at 8), and that Berntorp does not provide a disclosure on the multi-step process of using different models and aggregating those scores to an aggregate prioritization score (Remarks at 9). This is not persuasive because Luo discloses using different models to determine different prioritization scores in a single embodiment, and aggregating those scores into an aggregate prioritization score. The prima facie case of obviousness does not require Berntorp to teach features disclosed by Luo.
Claim 8 has not been amended to match the features of Claim 1.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20200202144 A1 – determining risk posed by another vehicle
US 20180307910 A1 – using models to track objects in video
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHADAN E HAGHANI whose telephone number is (571)270-5631. The examiner can normally be reached M-F 9AM - 5PM.
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, Jay Patel can be reached at 571-272-2988. 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.
/SHADAN E HAGHANI/ Examiner, Art Unit 2485