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 Arguments
Amendments and remarks filed June 23, 2026 have been fully considered.
Rejections under 35 U.S.C. § 112 have been overcome due to amendments and remarks filed June 23, 2026.
Applicant’s arguments with respect to claim(s) 1-4, 6, 7, 21 have been considered but 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.
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.
Claim(s) 1-4, 6, 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over “Federated Reinforcement Learning-Based UAV Swarm System for Aerial Remote Sensing to Lee” in view of US 10924308 B1 to Crawford.
Regarding claim 1,
Lee teaches:
A method comprising:
generating, in a machine learning module, an operational model of a radar network within an environment, wherein an autonomous agent within the environment detects the radar network and the environment includes a plurality of autonomous agents; ([abs] – “in this paper, we propose the federated reinforcement learning- (FRL-) based UAV swarm system for aerial remote sensing. The proposed system applies reinforcement learning (RL) to UAV clusters to establish the SI in the UAV system. Furthermore, by combining federated learning (FL) with RL, the proposed system constructs the more reliable and robust SI for UAV systems.”)
generating, in a reinforcement learning module of a federated learning network, a counter-radar maneuver based on the operational model in response to classifying the radar network as non-friendly; (Examiner notes that the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. MPEP 2111.04. In this case, the “generating…” limitation is contingent upon the condition precedent “classifying the radar network as non-friendly.” Because the claimed invention may be practiced without the without the condition precedent occurring (i.e., the radar network is identified as friendly), the broadest reasonable interpretation of this claim does not require the contingent “generating…” step.) wherein generating includes:
selecting a past counter-radar maneuver from one of the plurality of autonomous agents in the federated learning network,
generating the counter-radar maneuver based on the past counter-radar maneuver from one of the plurality of autonomous agents and incoming sensor data from the autonomous agent;
implementing the counter-radar maneuver via the autonomous agent in communication with the reinforcement learning module. (Examiner notes that the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. MPEP 2111.04. In this case, the “implementing…” limitation is contingent upon the condition precedent “classifying the radar network as non-friendly” (because the counter-radar maneuver is only generated when the radar network is classified as non-friendly). Because the claimed invention may be practiced without the without the condition precedent occurring (i.e., the radar network is identified as friendly), the broadest reasonable interpretation of this claim does not require the contingent “implementing…” step.)
modifying the operational model to include the generated counter-radar maneuver; (Examiner notes that the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. MPEP 2111.04. In this case, the “modifying…” limitation is contingent upon the condition precedent “classifying the radar network as non-friendly” (because the model is only modified when the counter-radar maneuver is generated). Because the claimed invention may be practiced without the without the condition precedent occurring (i.e., the radar network is identified as friendly), the broadest reasonable interpretation of this claim does not require the contingent “modifying…” step.) and
transmitting the modified operational model with the generated counter-radar maneuver to another autonomous agent. (Examiner notes that the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. MPEP 2111.04. In this case, the “transmitting…” limitation is contingent upon the condition precedent “classifying the radar network as non-friendly” (because the model is only transmitted after being modified). Because the claimed invention may be practiced without the without the condition precedent occurring (i.e., the radar network is identified as friendly), the broadest reasonable interpretation of this claim does not require the contingent “transmitting…” step.)
Lee does not explicitly teach the additional elements of the claim.
However, Crawford teaches:
classifying the radar network as friendly or non-friendly based on the operational model; ([col. 2, lines 46-62] – “associating the PDWs with one or more RF emitters and identify the one or more RF emitters, by a second machine learning device.” [col. 2, lines 41-46] – “identifies and optionally locates radar signals and their characteristics, for example, what type of RF emitters or radars and whether they are friendly radars or “threat” radars.” [col. 7, lines 42-61] – “In some embodiments, the ML 316 may be a deep learning machine that uses multiple layers to progressively extract higher level features from the characterized pulses to associate them with certain type of emitter and identify the emitter”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied Crawford’s known technique to Lee’s known method ready for improvement to yield predictable results. Such a finding is proper because (1) Lee teaches a base method of radar detection and federated reinforcement learning by an agent ([4.1 – system concept] – “The UAVs continually move without any predetermined guidance or programmed function. At the same time, they repeatedly perform local learning based on their own actions and data collected from gas sensors and ranging sensors, such as LiDAR or radar. After that, the UAVs share only their locally trained models with each other periodically. During the mission, the UAVs repeat such moving, learning, and occasional sharing to build SI.”) ; (2) Crawford teaches a specific model for identifying friendly/foe radars; (3) Lee teaches ([1. Introduction] – “Motivated by the fact described above, in this paper, we propose the FRL-based UAV swarm system for aerial remote sensing. To show the application of our proposed system, we take a gas detection as an application example and propose the FRL-based gas sensing system using UAV swarm. However, since the proposed system is not designed to be specialized in specific applications, the system can be applied to any IIoT applications using UAVs.”) one of ordinary skill in the art would have recognized that applying the known technique would have yielded predictable results and resulted in a system with improved threat detection in UAV swarm; and (4) no additional findings based on the Graham factual inquiries are necessary, in view of the facts of the case under consideration, to explain a conclusion of obviousness (See MPEP 2143).
Regarding claim 2,
Lee in view of Crawford teaches:
The method of claim 1,
Lee does not explicitly teach the additional elements of the claim.
However, Crawford teaches:
wherein generating the operational model of the radar network includes:
separating a detected radio frequency (RF) signal into a set of signals, each signal of the set of signals corresponding to a respective emitter; (Figs. 3, 9; [col. 11, last para] – “As shown in block 902, a plurality of RF signals is received from one or more RF emitters, for example, one or more radars. In block 904, the RF signals are channelized into a plurality of channels, for example, by respective channelizer 304-1 to 304-N in FIG. 3”) and
estimating a descriptor for each signal of the set of signals, ([col. 12, lines 8-22] – “In block 910, pulses in each channel are detected, for example, by channelized pulse detection circuit 310 of FIG. 3… to produce pulse description words (PDWs)” [col. 10, second para] – “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.”) wherein the operational model is based on the estimated descriptor for each signal of the set of signals. ([col. 10, last para] – “An embedded layer 714 is where the PDW parameters are embedded into the model.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied Crawford’s known technique to Lee’s known method ready for improvement to yield predictable results. Such a finding is proper because (1) Lee teaches a base method of radar detection and federated reinforcement learning by an agent ([4.1 – system concept] – “The UAVs continually move without any predetermined guidance or programmed function. At the same time, they repeatedly perform local learning based on their own actions and data collected from gas sensors and ranging sensors, such as LiDAR or radar. After that, the UAVs share only their locally trained models with each other periodically. During the mission, the UAVs repeat such moving, learning, and occasional sharing to build SI.”) ; (2) Crawford teaches a specific model for identifying friendly/foe radars; (3) Lee teaches ([1. Introduction] – “Motivated by the fact described above, in this paper, we propose the FRL-based UAV swarm system for aerial remote sensing. To show the application of our proposed system, we take a gas detection as an application example and propose the FRL-based gas sensing system using UAV swarm. However, since the proposed system is not designed to be specialized in specific applications, the system can be applied to any IIoT applications using UAVs.”) one of ordinary skill in the art would have recognized that applying the known technique would have yielded predictable results and resulted in a system with improved threat detection in UAV swarm; and (4) no additional findings based on the Graham factual inquiries are necessary, in view of the facts of the case under consideration, to explain a conclusion of obviousness (See MPEP 2143).
Regarding claim 3,
Lee in view of Crawford teaches:
The method of claim 2,
Lee does not explicitly teach the additional elements of the claim.
However, Crawford teaches:
The method of claim 2, wherein the descriptor includes one of a bandwidth, a modulation, a pulse width discriminator, or a pulse repetition interval for the respective emitter. ([col. 10, second para] – “The output of the classifier 618 is a PDW that include the classical parameters of an RF emitter (e.g., a radar) pulse, including RF carrier, Time of Arrival (ToA), pulse width and modulation type.”)
Regarding claim 4,
Examiner notes that the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. MPEP 2111.04. In this case, the additional limitations of claim 4 further describe the generated counter-radar maneuver of claim 1, which is contingent upon the condition precedent “classifying the radar network as non-friendly.” Because the claimed invention may be practiced without the without the condition precedent occurring (i.e., the radar network is identified as friendly and therefore no counter-radar maneuver is generated, see also rejection and analysis of claim 1 above), the additional limitations recited in claim 4 are not required to be part of the claimed invention.
Regarding claim 6,
Examiner notes that the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. MPEP 2111.04. In this case, the additional limitations of claim 6 further describe the “transmitting” step of claim 1, which is contingent upon the condition precedent “classifying the radar network as non-friendly.” Because the claimed invention may be practiced without the without the condition precedent occurring (i.e., the radar network is identified as friendly and therefore no counter-radar maneuver is generated, therefore the operational model is not modified, and therefore a modified operational model is not transmitted, see also rejection and analysis of claim 1 above), the additional limitations recited in claim 6 are not required to be part of the claimed invention.
Regarding claim 21,
Examiner notes that the broadest reasonable interpretation of a method (or process) claim having contingent limitations requires only those steps that must be performed and does not include steps that are not required to be performed because the condition(s) precedent are not met. MPEP 2111.04. In this case, the additional limitations of claim 22 further describe the generated counter-radar maneuver of claim 1, which is contingent upon the condition precedent “classifying the radar network as non-friendly.” Because the claimed invention may be practiced without the without the condition precedent occurring (i.e., the radar network is identified as friendly and therefore no counter-radar maneuver is generated, see also rejection and analysis of claim 1 above), the additional limitations recited in claim 22 are not required to be part of the claimed invention.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over “Federated Reinforcement Learning-Based UAV Swarm System for Aerial Remote Sensing to Lee” in view of US 10924308 B1 to Crawford and further in view of US 20180341262 A1 to Yeshurun.
Regarding claim 7,
Lee in view of Crawford teaches:
The method of claim 1,
Lee does not explicitly teach the additional elements of the claim.
However, Yeshurun further teaches:
The method of claim 1, wherein a remote operator controls the autonomous agent. ([0037-38] – “Each of the UAVs 14 may be associated with a UAV controller (not illustrated) for directing its operation, in particular the operation of its elements… The UAV controller may be provided as an element of the UAV 14 or externally thereto,”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have applied Yeshurun’s known technique to Lee in view of Crawford’s known method ready for improvement to yield predictable results. Such a finding is proper because (1) Lee in view of Crawford teaches a base method of radar detection by an agent and a federated reinforcement learning model for UAV swarm (Lee [col. 4, lines 9-22] – “smart receiver or sensor that includes compressive sensing and machine learning capabilities for identifying and optionally locating RF signals… smart receiver or sensor that may be positioned on an airborne, ground or sea moving platform… in close proximity to the target RF emitters (e.g., radars) the signals of which are to be detected.”), radar network modeling, friendly/non-friendly identification, and generation and implementation of counter-radar maneuvers; (2) Yeshurun teaches a specific technique of detecting radar signals via an autonomous agent for purposes of threat identification and countermeasure deployment including an operator; (3) one of ordinary skill in the art would have recognized that applying the known technique would have yielded predictable results and resulted in a system with improved threat detection via UAVs; and (4) no additional findings based on the Graham factual inquiries are necessary, in view of the facts of the case under consideration, to explain a conclusion of obviousness (See MPEP 2143).
Allowable Subject Matter
Claims 8-11, 13-20, 22 indicated allowable.
The following is an examiner’s statement of reasons for allowance: The closest prior art of record (“Federated Reinforcement Learning-Based UAV Swarm System for Aerial Remote Sensing to Lee”; US 10924308 B1 to Crawford; US 20180341262 A1 to Yeshurun) neither teaches nor fairly renders obvious the combinations set forth in claims 8-11, 13-20, 22. See analysis regarding independent claim 8 below. Claim(s) 15 recite similar limitation(s) to claim 8 and is/are allowed for similar reasons. Dependent claims allowed at least as depending from allowed claims.
Regarding claim 8,
Lee teaches:
A system comprising:
a machine learning module configured to:
generate an operational model of a detected radar network within an environment, ([4.1 – system concept] – “The UAVs continually move without any predetermined guidance or programmed function. At the same time, they repeatedly perform local learning based on their own actions and data collected from gas sensors and ranging sensors, such as LiDAR or radar. After that, the UAVs share only their locally trained models with each other periodically. During the mission, the UAVs repeat such moving, learning, and occasional sharing to build SI.”) and
a reinforcement learning module of a federated learning network in communication with the machine learning module ([abs] – “in this paper, we propose the federated reinforcement learning- (FRL-) based UAV swarm system for aerial remote sensing. The proposed system applies reinforcement learning (RL) to UAV clusters to establish the SI in the UAV system. Furthermore, by combining federated learning (FL) with RL, the proposed system constructs the more reliable and robust SI for UAV systems.”)
Crawford teaches:
classifying the radar network as friendly or non-friendly based on the operational model; ([col. 2, lines 46-62] – “associating the PDWs with one or more RF emitters and identify the one or more RF emitters, by a second machine learning device.” [col. 2, lines 41-46] – “identifies and optionally locates radar signals and their characteristics, for example, what type of RF emitters or radars and whether they are friendly radars or “threat” radars.” [col. 7, lines 42-61] – “In some embodiments, the ML 316 may be a deep learning machine that uses multiple layers to progressively extract higher level features from the characterized pulses to associate them with certain type of emitter and identify the emitter”)
However, the prior art of record does not teach, in combination with the remaining elements of the claim:
a reinforcement learning module of a federated learning network in communication with the machine learning module and configured to generate a counter-radar maneuver based on the operational model in response to classifying the radar network as non-friendly; and
an autonomous agent in communication with the reinforcement learning module of the federated learning and configured to:
generate the counter-radar maneuver wherein generation includes, selecting a past counter-radar maneuver from one of a plurality of autonomous agents in the federated learning network, and generating the counter-radar maneuver based on the past counter- radar maneuver from one of the plurality of autonomous agents and incoming sensor data from the autonomous agent;
implement the counter-radar maneuver vias the autonomous agent in communication with the reinforcement learning module;
modify the operational model to include the generated counter-radar maneuver; and
transmit the modified operational model with the generated counter-radar maneuver to another autonomous agent.
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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JULIANA CROSS whose telephone number is (571)272-8721. The examiner can normally be reached Mon-Fri 9am-5pm Pacific time.
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, Resha Desai can be reached on (571) 270-7792. 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.
/JULIANA CROSS/Examiner, Art Unit 3648
/BRADY W FRAZIER/Primary Examiner, Art Unit 3648
Prosecution Insights