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
This action is in response to amendments and remarks filed on 03/26/2026. Claim(s) 1, 3, 10, 12-15, and 19 have been amended. Claim(s) 21 have been added. Claim(s) 1-21 are pending examination. Objections to the drawings, specification, and claims have been withdrawn in light of the instant amendments. Rejection to claim(s) 15 over the 35 USC 112(b) rejection has been withdrawn in light of the instant amendments. This action is made final.
Response to Arguments
Applicant presents the following argument(s) regarding the previous office action:
Applicant asserts that the 35 USC 102 rejection of independent claims 1, 10, and 19 is improper. Applicant asserts that the cited prior art does not teach the amended limitations of, “control operation of the battery…the first motive phase.”
Applicant asserts that the 35 USC 103 rejection of claims 7-9 and 16-18 is improper due to their dependence on allowable subject matter and the use of improper hindsight reasoning in their rejection.
Applicant’s arguments with respect to claim(s) 1, 10, and 19 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.
Regarding applicant’s argument A, the examiner finds it moot. Applicant’s argument is centered specifically on a newly amended limitation. After further search and consideration the examiner would rely on previously cited Richter (US PG Pub 2024/0127699) to teach these new limitations. Looking at newly cited portions of Richter, [0028] and [0041] Richter teaches that the system can adjust its power output to meet requirements of various motive phases. The output has a peak that it can adjust to as well as an average output of power. These peaks and averages are adjusted based on power capacity and the phase of flight. The system can provide more power depending on what phase the vehicle is in; i.e. more power for takeoff and landing when compared to the cruise phase. As [0028] recites, “energy source 204 may be used to provide electrical power to an electric aircraft or drone, such as an electric aircraft vehicle, during moments requiring high rates of power output, including without limitation takeoff, landing, thermal de-icing and situations requiring greater power output.” The teachings of Richter clearly show that the system can adjust how much power is output and during different phases this can vary. In light of this the examiner would continue to reject at least claims 1, 10, and 19 under 35 USC 102 as anticipated by Richter. Please see the section below titled, “Claim Rejections – 35 USC 102,” for more detailed mapping and explanation.
Applicant's arguments filed 03/26/2026 have been fully considered but they are not persuasive.
Regarding applicant’s argument B, the examiner respectfully disagrees. The examiner was not “overly generic,” rather the examiner used the phrase “all relate to the usage of ML models,” rather the examiner provided specific rationale for every 103 rejection in addition to this phrase, which was merely used to show that the arts being combined were related in their usage of ML models. This was determining the scope and contents of prior art as well as ascertaining the differences between them. After this phrase the examiner provided concrete rationale as to why one of ordinary skill in the art would combine the references, something the applicant asserts but does not provide evidence. Additionally, in response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971). In light of this the examiner would continue to reject claims 7-9 and 16-18 under 35 USC 103. Please see the section below titled, “Claim Rejections – 35 USC 103,” for more detailed mapping and explanation.
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 text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 1-6, 10-15, and 19-21 is/are rejected under 35 U.S.C. 102(a)(1)(a)(2) as being anticipated by Richter (US PG Pub 2024/0127699).
Regarding claim 1, Richter teaches an electric vehicle, ([0024], [0026], and [0028] teach an electric vehicle) comprising:
a battery providing electrical power for operation of the electric vehicle, ([0020], [0023], and [0028] teach the use of a battery providing power to an electric vehicle) wherein the operation of the electric vehicle comprises multiple motive phases that require different amount of electrical power; ([0020]-[0022], [0027], [0037], [0041], [0043], [0050], and [0053] teach that the EVTOL has a series of travel phases. These phases require varying amounts of power from the battery to carry out) and
one or more processors (Fig. 2, item 212; and [0037]-[0038] and [0042] teach a controller, i.e. processor, configured to carry out functions for controlling the aircraft) configured to:
predict one or more parameters associated with performance of the battery during at least a first motive phase of the multiple motive phases for current operation of the electric vehicle; (Fig. 4 in general, and [0049]-[0052] teaches the system “estimating” one or more parameters associated with the battery, in particular this prediction is the energy capacity. The system predicts the energy needs for every phase of the flight, which would include the first phase, i.e. takeoff) and
based on the prediction, control operation of the battery to dynamically adjust electrical power provided by the battery during the first motive phase for the current operation of the electric vehicle to manage the one or more parameters. ([0028] and [0041] teach the EVTOL having a series of power demands. The system can provide “peak power” when the system needs more power. This peak is extracted from the battery during phases of intense power demands including takeoff, i.e. the first motive phase)
Regarding claim 2, Richter teaches the electric vehicle of claim 1, wherein the electric vehicle is an electric Vertical Takeoff and Landing vehicle (eVOTL). ([0017] and Fig. 3 and [0045] teach the aircraft as an eVTOL)
Claims 11 and 20 are substantially similar and would be rejected for the same rationale as recited above.
Regarding claim 10, Richter teaches a non-transitory computer readable medium comprising instructions, that when read by one or more processors, cause the one or more processors to: ([0092]-[0094] teach the system having non-transitory memory and processors with instructions stored in memory that cause the processors to act in a specific way)
predict one or more parameters associated with performance of the battery during at least a first motive phase of multiple motive phases for current operation of the electric vehicle, (Fig. 4 in general, and [0049]-[0052] teaches the system “estimating” one or more parameters associated with the battery, in particular this prediction is the energy capacity. The system predicts the energy needs for every phase of the flight, which would include the first phase, i.e. takeoff) wherein the prediction is based on a machine learning model trained on data associated with performance of the battery during the multiple motive phases for previous operation of the electric vehicle; ([0052]-[0053] teach a ML algorithm trained on data from previous flights to determine the associated performance of the battery during subsequent flights/phases) and
based on the prediction, control operation of the battery to dynamically adjust electrical power provided by the battery during the first motive phase for the current operation of the electric vehicle to manage the one or more parameters. ([0028] and [0041] teach the EVTOL having a series of power demands. The system can provide “peak power” when the system needs more power. This peak is extracted from the battery during phases of intense power demands including takeoff, i.e. the first motive phase)
Claim and 19 is substantially similar and would be rejected for the same rationale as recited above.
Regarding claim 3, Richter teaches the electric vehicle of claim 2, wherein the multiple motive phases of operation comprise: take-off, hovering, flight, and landing. ([0020], [0043], and [0050] teach the phases of the flight an aircraft can take as take-off, landing, taxiing., hovering, cruising, etc. this is equivalent to the claimed phases)
Claim 12 is substantially similar and would be rejected for the same rationale as recited above.
Regarding claim 4, Richter teaches the electric vehicle of claim 3, wherein the one or more parameters associated with performance of the battery comprise: electrical power output, ([0041] and [0048] and [0053] teach the measuring/estimating of power output in relation to estimated usable energy) State of Charge (SOC), ([0021] teaches estimating state of charge in relation to estimated usable energy) State of Health (SOH), ([0021] teaches estimating sate of health in relation to estimated usable energy) and battery temperature. ([0021] and [0039] teach a parameter of battery temperature in relation to estimated usable energy)
Claim 15 is substantially similar and would be rejected for the same rationale as recited above.
Regarding claim 5, Richter teaches the electric vehicle of claim 4, wherein the one or more processors are further configured to dynamically adjust functions related to the current operation of the eVOTL in real-time based on the prediction. ([0050] teaches modifying functions related to the flight based on the predicted values.)
Claim 13 is substantially similar and would be rejected for the same rationale as recited above.
Regarding claim 6, Richter teaches the electric vehicle of claim 5, wherein functions related to the current operation of the eVOTL comprise: planning energy usage, optimizing flight paths for energy efficiency, battery life management, and safety operations. ([0050] teaches the modification of aircraft operations in order to preserve energy. This includes modifying flight planes, planning energy use during the flight, preserving battery, and ensuring a safe landing, i.e. safety operation)
Claim 14 is substantially similar and would be rejected for the same rationale as recited above.
Regarding claim 21, Richter teaches the electric vehicle of claim 1, wherein controlling the battery to dynamically adjust the electrical power provided by the battery during the first motive phase for the current operation of the electric vehicle comprises controlling the battery at least partially independently from controlling motive characteristics of the electric vehicle. ([0028] teaches the system adjusting the power output of the energy device, i.e. battery, in order to adjust the battery operation independent from the control of flight surfaces, weather, etc.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
Claim(s) 7-8 and 16-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Richter in view of Sakemi ("Model-size reduction for reservoir computing by concatenating internal states through time") and Gallicchio ("Fast Spectral Radius Initialization for Recurrent Neural Networks").
Regarding claim 7, Richter teaches the electric vehicle of claim 1, wherein the one or more processors are further configured to perform ([0063] teaches the ML model controlling parameters of the battery. [0022] teaches the use of the ML model in flight, i.e. real-time)
Richter does not teach fast spectral initialization, delay-state concatenation and delay-state concatenation with transient states operations on the machine learning model.
However, Sakemi teaches “delay-state concatenation and delay-state concatenation with transient states operations on the machine learning model” (“Proposed Method” teaches the use of delay-state concatenation and delay-state concatenation with transient states, in order to reduce a model size for the generation of a reservoir computing model)
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date, to incorporate the teachings of Richter with Sakemi; and have a reasonable expectation of success. Both relate to the usage of ML models in reference to prediction systems. As Sakemi teaches in the proposed methods section “[These] methods share the idea that the number of the effective dimension of the reservoir is increased by allowing additional connections from the reservoir layer at multiple time steps to the output layer at the current time step. For the delay-state concatenation and delay-state concatenation with transient states, additional connections are formed from the past states of the reservoir layer to the current output layer.” This allows for systems in which forms nodal connections with both current nodes and future nodes. This allows the system to achieve a steady measurement state on initial startup of the ML model and allows the system to output accurate information.
The combination of Richter and Sakemi does not teach fast spectral initialization.
However, Gallicchio teaches “fast spectral initialization.” (Abstract, Section 1, and Section 3 “Fast Spectral Initialization” teach the use of fast spectral initialization to build a reservoir computing model with a desired spectral radius, this is done in order to enable efficient design of said networks in a time-series task with large datasets)
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date, to incorporate the teachings of Richter and Sakemi with Gallicchio; and have a reasonable expectation of success. All relate to the usage of ML models and systems for predicting outputs. As Gallicchio teaches in its Abstract and Introduction “the proposed approach allows us to overcome the typical computational bottleneck related to the eigendecomposition of large matrices, enabling to efficiently design large reservoir networks and hence to address time-series tasks characterized by medium/big datasets. Experimental results show that the proposed method enables an accurate control of the spectral radius of randomly initialized recurrent matrices, providing an initialization approach that is extremely more efficient compared to common RC practice.” This allows for the systems to quickly ready a stabilized matrix with large data on the initialization of the ML model. This allows for quick startup when the eVTOL starts its computers and begins to model the battery information.
Claim 16 is substantially similar and would be rejected for the same rationale as recited above.
Regarding claim 8, Richter teaches the electric vehicle of claim 7, wherein the machine learning model ([0067] teaches that the remote ML model can be stored and retrieved from a remote device)
Richter does not teach is trained in accordance with reservoir computing.
However, Sakemi teaches “is trained in accordance with reservoir computing.” (Abstract, Introduction; teach the use of a ML model trained in reservoir computing)
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date, to incorporate the teachings of Richter with Sakemi; and have a reasonable expectation of success. Both relate to the usage of ML models in reference to prediction systems. As Sakemi teaches in the introduction, “Reservoir computing (RC) is a machine-learning algorithm that aims to reduce the computational resources required for predicting time series without reducing accuracy… Because only the weights between the reservoir layer and the output layer are trained while the other weights remain fixed, the learning process of RC is much faster than that of backpropagation through time. Therefore, RC is expected to be a lightweight machine-learning algorithm that enables machine learning in edge computing.” This ensures that the system can quickly and efficiently train a machine learning model. The training does not lose accuracy despite the limitations of time specified data. This allows for fast and accurate models for these kind of time specific systems.
Claim 17 is substantially similar and would be rejected for the same rationale as recited above.
Claim(s) 9 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Richter, Sakemi, and Gallicchio in view of Goshtasbi (US PG Pub 2025/0102582).
Regarding claim 9, the combination of Richter, Sakemi, and Gallicchio teaches the electric vehicle of claim 8.
The combination of Richter, Sakemi, and Gallicchio does not teach wherein the one or more processors are further configured to validate the trained machine learning model in real-time during the current operation of the electric vehicle.
However, Goshtasbi teaches “wherein the one or more processors are further configured to validate the trained machine learning model in real-time during the current operation of the electric vehicle.” ([0149]-[0156] teach validation of model during real time for battery prediction performance)
It would have been prima facie obvious to one of ordinary skill in the art, before the effective filing date, to incorporate the teachings of Richter, Sakemi, and Gallicchio with Goshtasbi; and have a reasonable expectation of success. All relate to the control of vehicle systems and the operations of ML models. As Goshtasbi teaches in [0149], “validation of battery models focus on accuracy of predicted voltage…Therefore, the critical metric for evaluating battery model performance in eVTOL applications is reserve time prediction accuracy.” The ML model for a battery must be validated. By validating using real-time data the system ensures that it is as accurate as possible. This prevents issues with the model and issues with the time dependent data used by the model.
Claim 18 is substantially similar and would be rejected for the same rationale as recited above.
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 NICHOLAS STRYKER whose telephone number is (571)272-4659. The examiner can normally be reached Monday-Friday 7:30-5:00.
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, Christian Chace can be reached at (571) 272-4190. 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.
/N.S./Examiner, Art Unit 3665 /CHRISTIAN CHACE/Supervisory Patent Examiner, Art Unit 3665
Prosecution Insights