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 .
STATUS OF CLAIMS
This action is in response to the Applicant’s filing on 7/08/2025. Claims 1-20 are pending and are examined below.
SPECIFICATION
The disclosure is objected to because of the following informalities.
[0061]: “a processor readable medium have instructions” – this clause should rather read “a processor readable medium [[have]] having instructions”.
Appropriate correction is required.
CLAIM OBJECTIONS
Claim(s) 12 is/are objected to because of claim informalities.
As to claim 12, “a processor readable medium have instructions” – this clause should rather read “a processor readable medium [[have]] having instructions”.
Appropriate correction is required.
CLAIM REJECTIONS—35 U.S.C. § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim(s) 1-20 is/are rejected under 35 U.S.C. § 101 because the claims fail to pass the Alice/Mayo test for determining patent eligibility.
The patent eligibility test is performed below for independent claim(s) 1 and 12.
Step 1—Does the claim fall within a statutory category?
Claim 1: Yes, the claim recites a process.
Claim 12: Yes, the claim recites a machine or manufacture.
Step 2A, Prong One—Is a judicial exception recited?
Claim(s) 1 and 12 is/are provided below with the abstract idea indicated in bold and additional elements without bold.
1. A method comprising:
selecting a first data set including at least one first magnetic anomaly map of a given area, the at least one first magnetic anomaly map having a first accuracy;
selecting a second data set including geological data for the given area;
sending the first and second data sets to a machine learning model including a convolutional neural network;
generating at least one second magnetic anomaly map of the given area based on the first and second data sets, the at least one second magnetic anomaly map having a second accuracy that is higher than the first accuracy;
comparing the at least one second magnetic anomaly map with at least one ground truth map of the given area to train the machine learning model;
performing a validation test of the trained machine learning model, using a validation threshold, by sending an additional data set including held-out magnetic anomaly map data to the trained machine learning model; and
in response to the validation threshold being met, using the trained machine learning model to generate one or more higher accuracy magnetic anomaly maps of a selected area based on input magnetic anomaly map data.
12. A system comprising:
at least one processor;
a machine learning model including a convolutional neural network, the machine learning model in operative communication with the at least one processor; and
a processor readable medium have instructions, executable by the at least one processor, to perform a method of generating an enhanced magnetic anomaly map for use in a magnetic anomaly navigation filter of a vehicle navigation system, the method comprising:
generating a first data set including at least one first magnetic anomaly map of a given area, the at least one first magnetic anomaly map having a first accuracy;
generating a second data set including geological data for the given area;
sending the first and second data sets to the machine learning model;
generating at least one second magnetic anomaly map of the given area based on the first and second data sets sent to the machine learning model, the at least one second magnetic anomaly map having a second accuracy that is higher than the first accuracy;
comparing the at least one second magnetic anomaly map with at least one ground truth map of the given area to train the machine learning model; and
performing a validation test of the trained machine learning model, using a validation threshold, by sending an additional data set including held-out magnetic anomaly map data to the trained machine learning model;
wherein in response to the validation threshold being met, the trained machine learning model is deemed sufficient to generate one or more higher accuracy magnetic anomaly maps of selected areas based on input magnetic anomaly map data.
The above shows: yes, a judicial exception is recited. But for the additional elements, the claim limitation pertaining to selecting data sets, generating magnetic anomaly maps, comparing a magnetic anomaly map with a ground, determining whether a validation threshold has been met in a validation test, generating higher accuracy magnetic anomaly maps and deeming a trained machine learning model as sufficient truth map are processes which can practically be performed in the human mind with or without the use of a physical aid. Specifically:
a human mind is capable of selecting data sets through evaluation/judgment;
a human mind with the aid of pen and paper is capable of generating a magnetic anomaly map because the BRI of this step constitutes analyzing information through mathematical/logical steps and outputting the result of the analysis;1
a human mind is capable of comparing maps through evaluation/judgment;
a human mind is capable of determining whether a validation threshold has been met in a validation test through evaluation/judgment;
a human mind is capable of deeming a trained machine learning model as sufficient through evaluation/judgment.
The courts have held such forms of observation, evaluation, judgment, or opinion to represent the abstract idea of a mental process. As a result, the bolded limitations represent a mental process. Hence, the claim recites an abstract idea. (See MPEP § 2106.04(a)(2)(C)(III).)
Step 2A, Prong Two—Is the abstract idea integrated into a practical application?
No. The claims as a whole merely use generic computer components—i.e., processor, processor readable medium—that are recited at a high level of generality such that they cannot be considered more than mere instructions to apply the judicial exception using generic computer components. Therefore, the abstract idea is not integrated into a practical application.
Furthermore, the claimed machine learning model, convolutional neural network and associated limitations (e.g., train the machine learning model) do not integrate the abstract idea into a practical application because the claim is merely using the learning model in a generic fashion to apply the recited abstract ideas in a certain technological environment (i.e., magnetic anomaly map generation) without putting forth an improvement in how the learning model functions. Precedential case Recentive Analytics, Inc. v. Fox Corp.2 (hereinafter Recentive) held that “patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under § 101.” (Recentive, p. 18.) The court rationalized, “We have long recognized that ‘[a]n abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment,’” and “the application of existing technology to a novel database does not create patent eligibility.” (See Recentive, p. 14.) The court concluded that the claims are ineligible because “patents may be directed to abstract ideas where they disclose the use of an ‘already available [technology], with [its] already available basic functions, to use as [a] tool[] in executing the claimed process.’” (See Recentive, p. 15.)
Turning to the claimed invention, the claimed invention fails to set forth sufficient detail as to how the machine learning model accomplishes such in a way that differs from performing ordinary features of generic neural networks. Hence, following the analysis set forth by Recentive, the claimed learning model merely indicates a field of use or technological environment in which the judicial exception is performed. That is, the claim merely confines the use of the abstract idea to a particular technological environment (neural networks) and thus fails to add an inventive concept to the claims. (See MPEP 2106.05(h))
Step 2B—Does the claim provide an inventive concept?
No. The additional elements of the claims amount to either:
Insignificant pre-solution activity in the form of mere data gathering:
sending first and second data sets to a machine learning model
sending an additional data set including held-out magnetic anomaly map data to the trained machine learning model
Indication of field of use
for use in a magnetic anomaly navigation filter of a vehicle navigation system
Additionally, the claimed machine learning model and convolutional neural network does not provide an inventive concept because, as explained above, the claim is merely using the learning model in a generic fashion to apply the abstract idea without placing any limits on how the learning model functions, and the claim merely confines the use of the abstract idea to a particular technological environment (neural networks) and thus fails to add an inventive concept to the claims.
Claims 2-11 depend from claim 1 but do not render the claimed invention patent eligible because they are directed to additional mental steps:
find correlations between encoded geological data and magnetic anomaly values;
or insignificant extra-solution activity (e.g., gathering data):
storing one or more higher accuracy magnetic anomaly maps in a magnetic anomaly database;
retrieving one or more higher accuracy magnetic anomaly maps;
using one or more accuracy magnetic anomaly maps in a magnetic anomaly navigation filter in the navigation processing unit to aid in navigating the vehicle
The BRI of this claim encompasses insignificant post-solution activity such as displaying a map.
Claims 13-20 recite similar subject matter as claims 2-11 and therefore do not render the claimed invention as patent eligible for similar reasons.
Claims 1-20 do not pass the patent eligibility test. Accordingly, claims 1-20 are rejected under § 101.
CLAIM REJECTIONS—35 U.S.C § 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 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(s) 1 and 6 is/are rejected under 35 U.S.C. § 102(a)(1) as being anticipated by Machine Learning-Enhanced Interpolation of Gravity-Assisted Magnetic Data (NPL; “Xu”)3.
As to independent claim 1, Xu discloses a method comprising:
selecting a first data set including at least one first magnetic anomaly map of a given area, the at least one first magnetic anomaly map having a first accuracy (“This letter presents a deep learning-based magnetic data interpolation algorithm, enhancing resolution using LR gravity and magnetic data.” Section II. at p. 2. “The input data comprise two sets of LR gravity and magnetic anomaly data.” Caption for FIG. 2 at p. 2; see also FIG. 2.);
selecting a second data set including geological data for the given area (“Similar to magnetic data, gravity data also exhibit a certain degree of spatial correlation, as a single geological source may produce anomalies in both gravity and magnetic responses simultaneously.” Abstract. “Gravity data, being more responsive to the vertical distribution of geological bodies, overcomes vertical limitations in magnetic anomalies when combined.” Section I. at p. 2. “This letter presents a deep learning-based magnetic data interpolation algorithm, enhancing resolution using LR gravity and magnetic data.” Section II. at p. 2. “The input data comprise two sets of LR gravity and magnetic anomaly data.” Caption for FIG. 2 at p. 2. See also FIG. 2. Note: In light of the above, gravity data meets the BRI of geological data because it is a physical measurement indicative of geological structure of a given area.);
sending the first and second data sets to a machine learning model including a convolutional neural network (“The deep network consists of an encoder and a decoder, with its detailed structure depicted in Fig. 3. The input data comprise two sets of LR gravity and magnetic anomaly data, and the expected output is high-resolution (HR) magnetic anomaly data.” Caption for FIG. 2 at p. 2; see also FIG. 2. “The encoder conducts downsampling of the input image through convolutional layers and pooling layers, capturing intricate features, as illustrated in Fig. 3.” Section II. A. at p. 2; see also FIG. 3.);
generating at least one second magnetic anomaly map of the given area based on the first and second data sets, the at least one second magnetic anomaly map having a second accuracy that is higher than the first accuracy (“This letter presents a deep learning-based magnetic data interpolation algorithm, enhancing resolution using LR gravity and magnetic data.” Section II. at p. 2. “The input data comprise two sets of LR gravity and magnetic anomaly data, and the expected output is high-resolution (HR) magnetic anomaly data. …. This design allows the network to learn advanced features from LR data and generate corresponding HR magnetic anomaly data, providing an effective means for a more accurate representation of subsurface structures.” Caption for FIG. 2 at p. 2; see also FIGS. 2 and 3. See also Tables I and II which illustrate quantitative accuracy improvement over low-resolution input.);
comparing the at least one second magnetic anomaly map with at least one ground truth map of the given area to train the machine learning model (“The specific expression of the loss function is given by [Equation] (1). We utilize the mean square error (mse) to measure the difference between the predicted data and the actual answers.” Section II. at p. 2. “We utilized a synthetic sample model to compute the theoretical results (ground truth) after interpolation using the Coulomb magnetic formula, which were then compared with the network prediction results.” Section III. at p. 4. See also Tables I and II. );
performing a validation test of the trained machine learning model, using a validation threshold, by sending an additional data set including held-out magnetic anomaly map data to the trained machine learning model (“This study generated a total of 1500 data samples, comprising 1000 for training, 250 for validation, and 250 for testing purposes.” Section III. at p. 4. “To validate our proposed algorithm, we rigorously tested it on real data obtained from the Jinchuan mining region in Gansu Province, China. The magnetic and gravity anomaly data in this area exhibit significant homogeneity, making it suitable for interpolating magnetic anomalies using gravity data. Additionally, we subsampled the magnetic anomaly data and utilized the subsampled results for interpolation prediction, followed by comparison to validate the effectiveness of our method.” Section IV. at p. 4. See also Tables I and II which illustrate quantitative accuracy improvement over low-resolution input. Note: The 500 samples (250 for validation and 250 for testing) analogize to the BRI of held-out magnetic anomaly map data because they constitute map data withheld from training and used for validation/testing. Continuing, measuring a quantitative improvement over other methods (e.g., linear interpolation) analogizes to the BRI of a validation threshold because such represents a predetermined accuracy/error criterion that a model must satisfy to be considered as successfully outputting higher-resolution magnetic anomaly map data — such matches Applicant’s own success criterion of beating linear interpolation at PGPUB para. [0037].); and
in response to the validation threshold being met, using the trained machine learning model to generate one or more higher accuracy magnetic anomaly maps of a selected area based on input magnetic anomaly map data (“[T]his study employs deep learning algorithms for interpolating magnetic anomaly data, aiming to enhance the resolution of magnetic data. …. [T]he trained network is applied to measured data, with the input data being downsampled. The results show that the network can accurately predict magnetic anomaly data and bring them closer to the magnetic anomaly data before downsampling.” Abstract. See also Section 4 and Table II showcasing how a trained machine learning model meets a validation threshold against other methods. Note: Summarizing, when a trained machine learning model successfully meets a validation threshold, it is used to generate one or more higher accuracy magnetic anomaly maps of a selected area based on input magnetic anomaly map data.).
As to claim 6, Xu discloses: training the machine learning model to find correlations between encoded geological data and magnetic anomaly values (“[T]his study employs deep learning algorithms for interpolating magnetic anomaly data, aiming to enhance the resolution of magnetic data. …. [T]he trained network is applied to measured data, with the input data being downsampled. The results show that the network can accurately predict magnetic anomaly data and bring them closer to the magnetic anomaly data before downsampling.” Abstract. “Response between subsurface structural models and gravity-magnetic data, with the left side representing anomaly models of subsurface structures (having density and magnetization anomalies), and the right side displaying gravity anomaly data and magnetic anomaly data.” Caption for FIG. 1 at p. 1; see also FIG. 1. See also Section I. at pp. 1-2, discussing the relationship between magnetic anomaly data, gravity data and geological structure. See also FIGS. 4, 6. Note: Summarizing, the purpose of Xu is to train a machine learning model to output higher resolution magnetic anomaly map data based on correlating encoded geological data (gravity data) and magnetic anomaly values for a given area. Further, the gravity data is necessarily encoded as it requires to be encoded in order to be processed as input into the disclosed convolutional neural network.).
CLAIM REJECTIONS—35 U.S.C. § 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 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.
Claim(s) 2 is/are rejected under § 103 as being unpatentable over Xu in view of Lathrop et al. (US20240134085A1; “Lathrop”)
As to claim 2, Xu fails to explicitly disclose: storing the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly map database
Nevertheless, Lathrop teaches: storing the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly map database (“The anomaly map data are then displayed and/or stored for later use, as indicated at step 714. … [T]he anomaly map data are generated onboard the vehicle (e.g., by electronic processor 230 and/or machine learning controller 210) and then communicated to a remote user station (e.g., external device 104, server 106) where they are displayed to a user and/or stored for later use.” ¶ 110 and FIG. 7. “The server 106 may maintain a database.” ¶ 44 and FIG. 1.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu to include the feature of: storing the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly map database, as taught by Lathrop, with a reasonable expectation of success because this feature is useful for storing a generated magnetic anomaly map for later use in a vehicle navigation context. (See Lathrop, ¶ 110.)
Claim(s) 3 is/are rejected under § 103 as being unpatentable over Xu in view of Toutov et al. (US20220026212A1; “Toutov”)
As to claim 3, Xu fails to explicitly disclose: wherein the at least one first magnetic anomaly map comprises at least one North American Magnetic Anomaly Database (NAMAD) map, or at least one Earth Magnetic Anomaly Grid (EMAG) map.
Nevertheless, Toutov teaches: wherein the at least one first magnetic anomaly map comprises at least one Earth Magnetic Anomaly Grid (EMAG) map (“[T]he regional server can utilize the various correlation methods as described above to combine magnetic measurements received from different magnetic navigation devices and generate an updated geomagnetic map information such as … geomagnetic map patch or patches 820 to be sent to the main server 822. In particular embodiments, the main server 822 can combine EMAG data 824 with geomagnetic map patch data to generate an additional geomagnetic map layer with increased resolution relative to the EMAG data 824.” ¶ 62 and FIG. 8.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu to include the feature of: wherein the at least one first magnetic anomaly map comprises at least one Earth Magnetic Anomaly Grid (EMAG) map, as taught by Toutov, with a reasonable expectation of success because EMAG is well-known in the art as a reliable source for magnetic anomaly maps of the Earth’s surface.
Claim(s) 4 is/are rejected under § 103 as being unpatentable over Xu in view of Cuevas et al. (US20250225300A1; “Cuevas”)
As to claim 4, Xu discloses: wherein the convolutional neural network comprises a u-shaped architecture (“Network architecture utilized in this study is a U-shaped neural network comprising symmetrical encoder and decoder components.” Caption for FIG. 3 at p. 2; see also FIG. 3. “The encoder conducts downsampling of the input image through convolutional layers and pooling layers, capturing intricate features, as illustrated in Fig. 3.” Section II. A. at p. 2.).
Xu fails to explicitly disclose: wherein the convolutional neural network comprises a U-Net architecture.
Nevertheless, Cuevas teaches: wherein a convolutional neural network comprises a U-Net architecture (“[T]he image modeling manager 212 uses one or more of the resistivity image mapping machine-learning models 228 to generate horizon maps 224. The resistivity image mapping machine-learning models 228 may include different types of resistivity image mapping neural networks, such as image segmentation machine-learning models with neural network architectures (e.g., Monte Carlo Dropout prediction model, U-Net, U-Net++, Mask R-CNN, transformer-based models, large generative model-based segmentation neural networks, etc.).” Emphasis added; ¶ 56.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu to include the feature of: wherein a convolutional neural network comprises a U-Net architecture, as taught by Cuevas, with a reasonable expectation of success because U-Net architecture is a well-known model in the art known to be useful for image mapping. (See Cuevas, ¶ 56) Indeed, there would have been a reasonable expectation of success to incorporate Cuevas into Xu as Xu already contemplates utilizing a u-shaped CNN architecture; U-Net architecture is merely a more specific form of a u-shaped CNN architecture.
Claim(s) 5 is/are rejected under § 103 as being unpatentable over Xu in view of Moncayo et al. (US20240103185A1; “Moncayo”) and in view of A new generative adversarial network for medical images super resolution (NPL; “Ahmad”)4
As to claim 5, Xu discloses: wherein the at least one first magnetic anomaly map has a first height and a first width (See FIGS. 2, 4 and 6 which are spatial grid maps indexed by distance coordinates on both sides (i.e., height and width).).
Xu fails to explicitly disclose: the at least one second magnetic anomaly map has a second height that is double the first height, and a second width that is double the first width.
Nevertheless Moncayo teaches: a second magnetic anomaly map has a second height that is at least double the first height, and a second width that is at least double the first width (“The generator neural network can receive first geomagnetic map data corresponding to a first spatial resolution (e.g., lower resolution), and can output second geomagnetic map data having a spatial resolution that is higher than the first geomagnetic map data. Such an approach can be referred to as a ‘Super-Resolution’ GAN (SRGAN) generative framework for artificially-generated geomagnetic mapping.” ¶ 6. “FIG. 6A, FIG. 6B, and FIG. 6C show two-dimensional geomagnetic maps where FIG. 6A corresponds to a low-resolution map from a mathematical model …, with FIG. 6B showing the output of applying the SRGAN approach to FIG. 6A. … FIG. 7A, FIG. 7B, and FIG. 7C show two-dimensional geomagnetic maps where FIG. 7A corresponds to a low-resolution map from a mathematical model …, with FIG. 7B showing the output of applying the SRGAN approach to FIG. 7A.” ¶ 41 and FIGS. 6A-6B and FIGS. 7A-7B. Note: Summarizing, the application of SRGAN generates a second magnetic anomaly map with second height and widths that are at least double the first height and width, respectively.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu to include the feature of: a second magnetic anomaly map has a second height that is at least double the first height, and a second width that is at least double the first width, as taught by Moncayo, with a reasonable expectation of success because using super-resolution to generate a second magnetic anomaly map – thereby upscaling the dimensions of an input magnetic anomaly map – is useful to increase the resolution of the input magnetic anomaly map; such aligns with Xu’s goal of increasing the resolution of magnetic anomaly maps.
The combination of Xu and Moncayo fails to explicitly disclose: the second height and width are double the first height and width.
Nevertheless, Ahmad teaches: doubling a first height and width to a second height and width (The disclosure pertains to “retriev[ing] HR images from LR images using super-resolution (SR) methods.” Introduction at p. 1. Continuing, the SR methods are directed towards “Generative Adversarial Networks (GAN)” including “SRGAN” – see Introduction, Deep learning-based methods at p. 2. As part of performing super-resolution, “2x upscaling is performed” – see id. at p. 3; see also Methods at pp. 3-7.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Moncayo to include the feature of: doubling a first height and width to a second height and width, as taught by Ahmad, with a reasonable expectation of success because this feature is useful for meeting the design choice of 2x upscale and exploiting the advantages thereof. Indeed, a skilled artisan would have found it obvious to adjust Moncayo’s 4x scaling to 2x in view of Ahmad because such represents a routine design choice with no unexpected results or significant difference in function as opposed to 4x scaling. Ahmad demonstrates that 2x upscaling is a known design standard in the art, providing further motivation to only double height and width when generating a second magnetic anomaly map.
Claim(s) 7 and 9-11 is/are rejected under § 103 as being unpatentable over Xu in view of Lathrop as applied to claim 2 – further in view of Larsen et al. (US20160187142A1; “Larsen”)
As to claim 7, Xu fails to explicitly disclose: wherein the magnetic anomaly map database is located onboard a vehicle.
Nevertheless, Lathrop teaches: wherein the magnetic anomaly map database is located onboard a vehicle (“The anomaly map data are then displayed and/or stored for later use, as indicated at step 714. … [T]he anomaly map data are generated onboard the vehicle (e.g., by electronic processor 230 and/or machine learning controller 210) and then communicated to a remote user station (e.g., external device 104, server 106) where they are displayed to a user and/or stored for later use.” ¶ 110 and FIG. 7. “The server 106 may maintain a database.” ¶ 44 and FIG. 1. “Although the vehicle-based anomaly mapping system 100 is described as being in communication with an external device 104 or with a server 106, in some embodiments, the vehicle 102 used in the vehicle-based anomaly mapping system 100 is self-contained or closed, in terms of machine learning, and does not need to communicate with an external device 104, a server, or any other external system device to perform the functionality of the machine learning controller 110 described in more detail below.” Emphasis added; ¶ 58.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu to include the feature of: wherein the magnetic anomaly map database is located onboard a vehicle, as taught by Lathrop, with a reasonable expectation of success because this feature is useful for storing a generated magnetic anomaly map for later use in a vehicle navigation context. (See Lathrop, ¶ 110.)
The combination of Xu and Lathrop fails to explicitly disclose: wherein the magnetic anomaly map database is located in a navigation processing unit onboard a vehicle.
Nevertheless, Larsen teaches: wherein a magnetic anomaly map database is located in a navigation processing unit onboard a vehicle (“The INS 10 can be implemented in the control electronics of a vehicle. The vehicle can be any of a variety of vehicles, such as a land vehicle, watercraft, aircraft, or spacecraft, and which can be manned or unmanned. As another example, the vehicle can be a small vehicle, such as a small automated vehicle (e.g., an interplanetary rover) or even a person.” ¶ 14 and FIG. 1. “[A]s described herein, the INS 10 can incorporate the magnetic anomaly data NAV.sub.M to provide an improved navigation aiding solution over typical navigation aiding solutions.” ¶ 22.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Lathrop to include the feature of: wherein a magnetic anomaly map database is located in a navigation processing unit onboard a vehicle, as taught by Larsen, with a reasonable expectation of success because this feature is useful for exploiting Xu’s higher resolution magnetic anomaly maps for a vehicle navigation context.
As to claim 9, Xu fails to explicitly disclose: wherein the vehicle is an aerial vehicle.
Nevertheless, Lathrop teaches: wherein the vehicle is an aerial vehicle (“[T]he vehicle-based geophysical sensor system can include an aerial vehicle” - ¶ 32.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu with the feature of: wherein the vehicle is an aerial vehicle, as taught by Lathrop, with a reasonable expectation of success because it is well-known the art that vehicles, including aerial vehicles, utilize magnetic anomaly maps for navigation.
As to claim 10, Xu fails to explicitly disclose: wherein the vehicle comprises a crewed aircraft, or an uncrewed aircraft.
Nevertheless, Lathrop teaches: wherein the vehicle comprises an uncrewed aircraft (“[T]he vehicle-based geophysical sensor system can include an aerial vehicle, such as an unmanned aerial vehicle (‘UAV’)” - ¶ 32.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu with the feature of: wherein the vehicle comprises an uncrewed aircraft, as taught by Lathrop, with a reasonable expectation of success because it is well-known the art that vehicles, including an uncrewed aircraft, utilize magnetic anomaly maps for navigation.
As to claim 11, Xu fails to explicitly disclose: wherein the vehicle comprises a ground vehicle, or a water vehicle.
Nevertheless, Lathrop teaches: wherein the vehicle comprises a ground vehicle, or a water vehicle (“[T]he vehicle 102 may be an unmanned ground vehicle (‘UGV’), an unmanned underwater vehicle (‘UUV’)” - ¶ 40.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu with the feature of: wherein the vehicle comprises a ground vehicle, or a water vehicle, as taught by Lathrop, with a reasonable expectation of success because it is well-known the art that vehicles, including ground and water vehicles, utilize magnetic anomaly maps for navigation.
Claim(s) 8 is/are rejected under § 103 as being unpatentable over Xu in view of Lathrop and in view of Larsen as applied to claim 7 – further in view of Neary et al. (US12055393B1; “Neary”)
As to claim 8, Xu fails to explicitly disclose: retrieving the one or more higher accuracy magnetic anomaly maps from the magnetic anomaly map database.
Nevertheless, Lathrop teaches: retrieving the one or more higher accuracy magnetic anomaly maps from the magnetic anomaly map database (“The anomaly map data are then displayed and/or stored for later use, as indicated at step 714. … [T]he anomaly map data are generated onboard the vehicle (e.g., by electronic processor 230 and/or machine learning controller 210) and then communicated to a remote user station (e.g., external device 104, server 106) where they are displayed to a user and/or stored for later use.” ¶ 110 and FIG. 7.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu to include the feature of: retrieving the one or more higher accuracy magnetic anomaly maps from the magnetic anomaly map database, as taught by Lathrop, with a reasonable expectation of success because this feature is useful for storing a generated magnetic anomaly map for later use in a vehicle navigation context. (See Lathrop, ¶ 110.)
The combination of Xu, Lathrop and Larsen fails to explicitly disclose: using the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly navigation filter in the navigation processing unit to aid in navigating the vehicle.
Nevertheless, Neary teaches: using a higher accuracy magnetic anomaly maps in a magnetic anomaly navigation filter in a navigation processing unit to aid in navigating the vehicle (“Geophysical field map(s) can be loaded and processed during real-time operations. Such loading and processing enables a navigation filter to perform map matching in real-time to determine a position estimate. Additionally, machine learning based de-noising of geophysical data, e.g., magnetic and/or gravitational data can remove platform and environmental noise in the measurement data in real-time, and therefore reduce an error in position estimation otherwise produced by the navigation filter.” Col. 2, ll. 3-18.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu, Lathrop and Larsen to include the feature of: using a higher accuracy magnetic anomaly maps in a magnetic anomaly navigation filter in a navigation processing unit to aid in navigating the vehicle, as taught by Neary, with a reasonable expectation of success because this feature is useful for reducing error in position estimation otherwise produced by a navigation filter in the context of magnetic anomaly map generation. (See Neary, Col. 2, ll. 3-18.)
Claim(s) 12 and 17 is/are rejected under § 103 as being unpatentable over Xu in view of Neary.
As to independent claim 12, Xu discloses a system comprising:
a machine learning model including a convolutional neural network (“The deep network consists of an encoder and a decoder, with its detailed structure depicted in Fig. 3. The input data comprise two sets of LR gravity and magnetic anomaly data, and the expected output is high-resolution (HR) magnetic anomaly data.” Caption for FIG. 2 at p. 2; see also FIG. 2. “The encoder conducts downsampling of the input image through convolutional layers and pooling layers, capturing intricate features, as illustrated in Fig. 3.” Section II. A. at p. 2; see also FIG. 3.);
and means for:
generating a first data set including at least one first magnetic anomaly map of a given area, the at least one first magnetic anomaly map having a first accuracy (“This letter presents a deep learning-based magnetic data interpolation algorithm, enhancing resolution using LR gravity and magnetic data.” Section II. at p. 2. “The input data comprise two sets of LR gravity and magnetic anomaly data.” Caption for FIG. 2 at p. 2; see also FIG. 2.);
generating a second data set including geological data for the given area (“Similar to magnetic data, gravity data also exhibit a certain degree of spatial correlation, as a single geological source may produce anomalies in both gravity and magnetic responses simultaneously.” Abstract. “Gravity data, being more responsive to the vertical distribution of geological bodies, overcomes vertical limitations in magnetic anomalies when combined.” Section I. at p. 2. “This letter presents a deep learning-based magnetic data interpolation algorithm, enhancing resolution using LR gravity and magnetic data.” Section II. at p. 2. “The input data comprise two sets of LR gravity and magnetic anomaly data.” Caption for FIG. 2 at p. 2. See also FIG. 2. Note: In light of the above, gravity data meets the BRI of geological data because it is a physical measurement indicative of geological structure of a given area.);
sending the first and second data sets to the machine learning model (“The deep network consists of an encoder and a decoder, with its detailed structure depicted in Fig. 3. The input data comprise two sets of LR gravity and magnetic anomaly data, and the expected output is high-resolution (HR) magnetic anomaly data.” Caption for FIG. 2 at p. 2; see also FIG. 2. “The encoder conducts downsampling of the input image through convolutional layers and pooling layers, capturing intricate features, as illustrated in Fig. 3.” Section II. A. at p. 2; see also FIG. 3.);
generating at least one second magnetic anomaly map of the given area based on the first and second data sets sent to the machine learning model, the at least one second magnetic anomaly map having a second accuracy that is higher than the first accuracy (“This letter presents a deep learning-based magnetic data interpolation algorithm, enhancing resolution using LR gravity and magnetic data.” Section II. at p. 2. “The input data comprise two sets of LR gravity and magnetic anomaly data, and the expected output is high-resolution (HR) magnetic anomaly data. …. This design allows the network to learn advanced features from LR data and generate corresponding HR magnetic anomaly data, providing an effective means for a more accurate representation of subsurface structures.” Caption for FIG. 2 at p. 2; see also FIGS. 2 and 3. See also Tables I and II which illustrate quantitative accuracy improvement over low-resolution input.);
comparing the at least one second magnetic anomaly map with at least one ground truth map of the given area to train the machine learning model (“The specific expression of the loss function is given by [Equation] (1). We utilize the mean square error (mse) to measure the difference between the predicted data and the actual answers.” Section II. at p. 2. “We utilized a synthetic sample model to compute the theoretical results (ground truth) after interpolation using the Coulomb magnetic formula, which were then compared with the network prediction results.” Section III. at p. 4. See also Tables I and II. );
performing a validation test of the trained machine learning model, using a validation threshold, by sending an additional data set including held-out magnetic anomaly map data to the trained machine learning model (“This study generated a total of 1500 data samples, comprising 1000 for training, 250 for validation, and 250 for testing purposes.” Section III. at p. 4. “To validate our proposed algorithm, we rigorously tested it on real data obtained from the Jinchuan mining region in Gansu Province, China. The magnetic and gravity anomaly data in this area exhibit significant homogeneity, making it suitable for interpolating magnetic anomalies using gravity data. Additionally, we subsampled the magnetic anomaly data and utilized the subsampled results for interpolation prediction, followed by comparison to validate the effectiveness of our method.” Section IV. at p. 4. See also Tables I and II which illustrate quantitative accuracy improvement over low-resolution input. Note: The 500 samples (250 for validation and 250 for testing) analogize to the BRI of held-out magnetic anomaly map data because they constitute map data withheld from training and used for validation/testing. Continuing, measuring a quantitative improvement over other methods (e.g., linear interpolation) analogizes to the BRI of a validation threshold because such represents a predetermined accuracy/error criterion that a model must satisfy to be considered as successfully outputting higher-resolution magnetic anomaly map data — such matches Applicant’s own success criterion of beating linear interpolation at PGPUB para. [0037].); and
in response to the validation threshold being met, the trained machine learning model is deemed sufficient to generate one or more higher accuracy magnetic anomaly maps of selected areas based on input magnetic anomaly map data (“[T]his study employs deep learning algorithms for interpolating magnetic anomaly data, aiming to enhance the resolution of magnetic data. …. [T]he trained network is applied to measured data, with the input data being downsampled. The results show that the network can accurately predict magnetic anomaly data and bring them closer to the magnetic anomaly data before downsampling.” Abstract. See also Section 4 and Table II showcasing how a trained machine learning model meets a validation threshold against other methods. Note: Summarizing, when a trained machine learning model successfully meets a validation threshold, it is used to generate one or more higher accuracy magnetic anomaly maps of a selected area based on input magnetic anomaly map data.).
Xu fails to explicitly disclose:
at least one processor;
the machine learning model in operative communication with the at least one processor; and
a processor readable medium have instructions, executable by the at least one processor, to perform a method of generating an enhanced magnetic anomaly map for use in a magnetic anomaly navigation filter of a vehicle navigation system.
Nevertheless, Neary teaches:
at least one processor (“magnetometer measurement processor” – see col. 3, ll. 39-55 and FIG. 1.);
the machine learning model in operative communication with the at least one processor (“Turning next to the magnetometer measurement processor 110, mag-bridge 114 ingests magnetometer measurements. Mag-bridge is a de-noising system. In different embodiments, the magnetometer measurements can pass through a Tolles-Lawson model first and then through a de-noising machine learning (ML) model or the magnetometer measurements can go through a de-noising machine learning model first and then pass through a Tolles-Lawson model or the magnetometer measurements can go through both models at the same time.” Col. 3, ll. 39-55 and FIG. 1.); and
a processor readable medium have instructions, executable by the at least one processor, to perform a method of generating an enhanced magnetic anomaly map for use in a magnetic anomaly navigation filter of a vehicle navigation system (“Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible non-transitory storage medium for execution by, or to control the operation of, data processing apparatus.” Col. 13, ll. 50-67 and col. 14 ll. 1-3. “Geophysical field map(s) can be loaded and processed during real-time operations. Such loading and processing enables a navigation filter to perform map matching in real-time to determine a position estimate. Additionally, machine learning based de-noising of geophysical data, e.g., magnetic and/or gravitational data can remove platform and environmental noise in the measurement data in real-time, and therefore reduce an error in position estimation otherwise produced by the navigation filter.” Col. 2, ll. 3-18.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu with the features of: at least one processor; the machine learning model in operative communication with the at least one processor; and a processor readable medium have instructions, executable by the at least one processor, to perform a method of generating an enhanced magnetic anomaly map for use in a magnetic anomaly navigation filter of a vehicle navigation system, as taught by Neary, with a reasonable expectation of success because these features are well-known computer components in the art utilized for machine learning and magnetic anomaly map generation. Furthermore, these features are useful for reducing error in position estimation otherwise produced by a navigation filter in the context of magnetic anomaly map generation. (See Neary, Col. 2, ll. 3-18.)
As to claim 17, Xu discloses: training the machine learning model to find correlations between encoded geological data and magnetic anomaly values (“[T]his study employs deep learning algorithms for interpolating magnetic anomaly data, aiming to enhance the resolution of magnetic data. …. [T]he trained network is applied to measured data, with the input data being downsampled. The results show that the network can accurately predict magnetic anomaly data and bring them closer to the magnetic anomaly data before downsampling.” Abstract. “Response between subsurface structural models and gravity-magnetic data, with the left side representing anomaly models of subsurface structures (having density and magnetization anomalies), and the right side displaying gravity anomaly data and magnetic anomaly data.” Caption for FIG. 1 at p. 1; see also FIG. 1. See also Section I. at pp. 1-2, discussing the relationship between magnetic anomaly data, gravity data and geological structure. See also FIGS. 4, 6. Note: Summarizing, the purpose of Xu is to train a machine learning model to output higher resolution magnetic anomaly map data based on correlating encoded geological data (gravity data) and magnetic anomaly values for a given area. Further, the gravity data is necessarily encoded as it requires to be encoded in order to be processed as input into the disclosed convolutional neural network.).
Claim(s) 13 is/are rejected under § 103 as being unpatentable over Xu in view of Neary as applied to claim 12 – further in view of Lathrop.
As to claim 13, the combination of Xu and Neary fails to explicitly disclose: storing the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly map database
Nevertheless, Lathrop teaches: storing the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly map database (“The anomaly map data are then displayed and/or stored for later use, as indicated at step 714. … [T]he anomaly map data are generated onboard the vehicle (e.g., by electronic processor 230 and/or machine learning controller 210) and then communicated to a remote user station (e.g., external device 104, server 106) where they are displayed to a user and/or stored for later use.” ¶ 110 and FIG. 7. “The server 106 may maintain a database.” ¶ 44 and FIG. 1.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Neary to include the feature of: storing the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly map database, as taught by Lathrop, with a reasonable expectation of success because this feature is useful for storing a generated magnetic anomaly map for later use in a vehicle navigation context. (See Lathrop, ¶ 110.)
Claim(s) 14is/are rejected under § 103 as being unpatentable over Xu in view of Neary as applied to claim 12 – further in view of Toutov
As to claim 14, the combination of Xu and Neary fails to explicitly disclose: wherein the at least one first magnetic anomaly map comprises at least one North American Magnetic Anomaly Database (NAMAD) map, or at least one Earth Magnetic Anomaly Grid (EMAG) map.
Nevertheless, Toutov teaches: wherein the at least one first magnetic anomaly map comprises at least one Earth Magnetic Anomaly Grid (EMAG) map (“[T]he regional server can utilize the various correlation methods as described above to combine magnetic measurements received from different magnetic navigation devices and generate an updated geomagnetic map information such as … geomagnetic map patch or patches 820 to be sent to the main server 822. In particular embodiments, the main server 822 can combine EMAG data 824 with geomagnetic map patch data to generate an additional geomagnetic map layer with increased resolution relative to the EMAG data 824.” ¶ 62 and FIG. 8.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Neary to include the feature of: wherein the at least one first magnetic anomaly map comprises at least one Earth Magnetic Anomaly Grid (EMAG) map, as taught by Toutov, with a reasonable expectation of success because EMAG is well-known in the art as a reliable source for magnetic anomaly maps of the Earth’s surface.
Claim(s) 15 is/are rejected under § 103 as being unpatentable over Xu in view of Neary as applied to claim 12 — further in view of Cuevas.
As to claim 15, Xu discloses: wherein the convolutional neural network comprises a u-shaped architecture (“Network architecture utilized in this study is a U-shaped neural network comprising symmetrical encoder and decoder components.” Caption for FIG. 3 at p. 2; see also FIG. 3. “The encoder conducts downsampling of the input image through convolutional layers and pooling layers, capturing intricate features, as illustrated in Fig. 3.” Section II. A. at p. 2.).
The combination of Xu and Neary fails to explicitly disclose: wherein the convolutional neural network comprises a U-Net architecture.
Nevertheless, Cuevas teaches: wherein a convolutional neural network comprises a U-Net architecture (“[T]he image modeling manager 212 uses one or more of the resistivity image mapping machine-learning models 228 to generate horizon maps 224. The resistivity image mapping machine-learning models 228 may include different types of resistivity image mapping neural networks, such as image segmentation machine-learning models with neural network architectures (e.g., Monte Carlo Dropout prediction model, U-Net, U-Net++, Mask R-CNN, transformer-based models, large generative model-based segmentation neural networks, etc.).” Emphasis added; ¶ 56.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Neary to include the feature of: wherein a convolutional neural network comprises a U-Net architecture, as taught by Cuevas, with a reasonable expectation of success because U-Net architecture is a well-known model in the art known to be useful for image mapping. (See Cuevas, ¶ 56) Indeed, there would have been a reasonable expectation of success to incorporate Cuevas into Xu as Xu already contemplates utilizing a u-shaped CNN architecture; U-Net architecture is merely a more specific form of a u-shaped CNN architecture.
Claim(s) 16 is/are rejected under § 103 as being unpatentable over Xu in view of Neary as applied to claim 12 — further in view of Moncayo and in view of Ahmad.
As to claim 16, Xu discloses: wherein the at least one first magnetic anomaly map has a first height and a first width (See FIGS. 2, 4 and 6 which are spatial grid maps indexed by distance coordinates on both sides (i.e., height and width).).
Xu fails to explicitly disclose: the at least one second magnetic anomaly map has a second height that is double the first height, and a second width that is double the first width.
Nevertheless Moncayo teaches: a second magnetic anomaly map has a second height that is at least double the first height, and a second width that is at least double the first width (“The generator neural network can receive first geomagnetic map data corresponding to a first spatial resolution (e.g., lower resolution), and can output second geomagnetic map data having a spatial resolution that is higher than the first geomagnetic map data. Such an approach can be referred to as a ‘Super-Resolution’ GAN (SRGAN) generative framework for artificially-generated geomagnetic mapping.” ¶ 6. “FIG. 6A, FIG. 6B, and FIG. 6C show two-dimensional geomagnetic maps where FIG. 6A corresponds to a low-resolution map from a mathematical model …, with FIG. 6B showing the output of applying the SRGAN approach to FIG. 6A. … FIG. 7A, FIG. 7B, and FIG. 7C show two-dimensional geomagnetic maps where FIG. 7A corresponds to a low-resolution map from a mathematical model …, with FIG. 7B showing the output of applying the SRGAN approach to FIG. 7A.” ¶ 41 and FIGS. 6A-6B and FIGS. 7A-7B. Note: Summarizing, the application of SRGAN generates a second magnetic anomaly map with second height and widths that are at least double the first height and width, respectively.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Neary to include the feature of: a second magnetic anomaly map has a second height that is at least double the first height, and a second width that is at least double the first width, as taught by Moncayo, with a reasonable expectation of success because using super-resolution to generate a second magnetic anomaly map – thereby upscaling the dimensions of an input magnetic anomaly map – is useful to increase the resolution of the input magnetic anomaly map; such aligns with Xu’s goal of increasing the resolution of magnetic anomaly maps.
The combination of Xu, Neary and Moncayo fails to explicitly disclose: the second height and width are double the first height and width.
Nevertheless, Ahmad teaches: doubling a first height and width to a second height and width (The disclosure pertains to “retriev[ing] HR images from LR images using super-resolution (SR) methods.” Introduction at p. 1. Continuing, the SR methods are directed towards “Generative Adversarial Networks (GAN)” including “SRGAN” – see Introduction, Deep learning-based methods at p. 2. As part of performing super-resolution, “2x upscaling is performed” – see id. at p. 3; see also Methods at pp. 3-7.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu, Neary and Moncayo to include the feature of: doubling a first height and width to a second height and width, as taught by Ahmad, with a reasonable expectation of success because this feature is useful for meeting the design choice of 2x upscale and exploiting the advantages thereof. Indeed, a skilled artisan would have found it obvious to adjust Moncayo’s 4x scaling to 2x in view of Ahmad because such represents a routine design choice with no unexpected results or significant difference in function as opposed to 4x scaling. Ahmad demonstrates that 2x upscaling is a known design standard in the art, providing further motivation to only double height and width when generating a second magnetic anomaly map.
Claim(s) 18-20 is/are rejected under § 103 as being unpatentable over Xu in view of Leary and in view of Lathrop as applied to claim 13 – further in view of Larsen.
As to claim 18, the combination of Xu and Neary fails to explicitly disclose: wherein the magnetic anomaly map database is located onboard a vehicle.
Nevertheless, Lathrop teaches: wherein the magnetic anomaly map database is located onboard a vehicle (“The anomaly map data are then displayed and/or stored for later use, as indicated at step 714. … [T]he anomaly map data are generated onboard the vehicle (e.g., by electronic processor 230 and/or machine learning controller 210) and then communicated to a remote user station (e.g., external device 104, server 106) where they are displayed to a user and/or stored for later use.” ¶ 110 and FIG. 7. “The server 106 may maintain a database.” ¶ 44 and FIG. 1. “Although the vehicle-based anomaly mapping system 100 is described as being in communication with an external device 104 or with a server 106, in some embodiments, the vehicle 102 used in the vehicle-based anomaly mapping system 100 is self-contained or closed, in terms of machine learning, and does not need to communicate with an external device 104, a server, or any other external system device to perform the functionality of the machine learning controller 110 described in more detail below.” Emphasis added; ¶ 58.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Neary to include the feature of: wherein the magnetic anomaly map database is located onboard a vehicle, as taught by Lathrop, with a reasonable expectation of success because this feature is useful for storing a generated magnetic anomaly map for later use in a vehicle navigation context. (See Lathrop, ¶ 110.)
The combination of Xu, Leary and Lathrop fails to explicitly disclose: wherein the magnetic anomaly map database is located in a navigation processing unit onboard a vehicle.
Nevertheless, Larsen teaches: wherein a magnetic anomaly map database is located in a navigation processing unit onboard a vehicle (“The INS 10 can be implemented in the control electronics of a vehicle. The vehicle can be any of a variety of vehicles, such as a land vehicle, watercraft, aircraft, or spacecraft, and which can be manned or unmanned. As another example, the vehicle can be a small vehicle, such as a small automated vehicle (e.g., an interplanetary rover) or even a person.” ¶ 14 and FIG. 1. “[A]s described herein, the INS 10 can incorporate the magnetic anomaly data NAV.sub.M to provide an improved navigation aiding solution over typical navigation aiding solutions.” ¶ 22.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu, Leary and Lathrop to include the feature of: wherein a magnetic anomaly map database is located in a navigation processing unit onboard a vehicle, as taught by Larsen, with a reasonable expectation of success because this feature is useful for exploiting Xu’s higher resolution magnetic anomaly maps for a vehicle navigation context.
As to claim 19, Xu fails to explicitly disclose: using the one or more higher accuracy magnetic anomaly maps in a magnetic anomaly navigation filter in the navigation processing unit to aid in navigating the vehicle.
Nevertheless, Neary teaches: using a higher accuracy magnetic anomaly maps in a magnetic anomaly navigation filter in a navigation processing unit to aid in navigating the vehicle (“Geophysical field map(s) can be loaded and processed during real-time operations. Such loading and processing enables a navigation filter to perform map matching in real-time to determine a position estimate. Additionally, machine learning based de-noising of geophysical data, e.g., magnetic and/or gravitational data can remove platform and environmental noise in the measurement data in real-time, and therefore reduce an error in position estimation otherwise produced by the navigation filter.” Col. 2, ll. 3-18.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu to include the feature of: using a higher accuracy magnetic anomaly maps in a magnetic anomaly navigation filter in a navigation processing unit to aid in navigating the vehicle, as taught by Neary, with a reasonable expectation of success because this feature is useful for reducing error in position estimation otherwise produced by a navigation filter in the context of magnetic anomaly map generation. (See Neary, Col. 2, ll. 3-18.)
The combination of Xu and Neary fails to explicitly disclose: retrieving the one or more higher accuracy magnetic anomaly maps from the magnetic anomaly map database.
Nevertheless, Lathrop teaches: retrieving the one or more higher accuracy magnetic anomaly maps from the magnetic anomaly map database (“The anomaly map data are then displayed and/or stored for later use, as indicated at step 714. … [T]he anomaly map data are generated onboard the vehicle (e.g., by electronic processor 230 and/or machine learning controller 210) and then communicated to a remote user station (e.g., external device 104, server 106) where they are displayed to a user and/or stored for later use.” ¶ 110 and FIG. 7.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combination of Xu and Neary to include the feature of: retrieving the one or more higher accuracy magnetic anomaly maps from the magnetic anomaly map database, as taught by Lathrop, with a reasonable expectation of success because this feature is useful for storing a generated magnetic anomaly map for later use in a vehicle navigation context. (See Lathrop, ¶ 110.)
As to claim 20, combination of Xu and Neary fails to explicitly disclose: wherein the vehicle comprises an aerial vehicle, ground vehicle or a water vehicle.
Nevertheless, Lathrop teaches: wherein the vehicle is an aerial vehicle (“[T]he vehicle-based geophysical sensor system can include an aerial vehicle” - ¶ 32.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Xu with the feature of: wherein the vehicle is an aerial vehicle, as taught by Lathrop, with a reasonable expectation of success because it is well-known the art that vehicles, including aerial vehicles, utilize magnetic anomaly maps for navigation.
CONCLUSION
Any inquiry concerning this communication or earlier communications from the Examiner should be directed to Mario C. Gonzalez whose telephone number is (571) 272-5633. The Examiner can normally be reached M–F, 10:00–6:00 ET.
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, Fadey S. Jabr, can be reached on (571) 272-1516. 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.
/MARIO C GONZALEZ/Examiner, Art Unit 3668
1 See discussion of Electric Power Group at MPEP 2106.04(a)(2)(III.)(A.) describing how a claim to “collecting information, analyzing it, and displaying certain results of the collection and analysis” constitutes a mental process.
2 Recentive Analytics, Inc. v. Fox Corp., 134 F.4th 1205 (Fed. Cir. 2025)
3 H. Xu, L. Zhao, P. Jing, J. Yan, X. Zhu and Z. Jia, "Machine Learning-Enhanced Interpolation of Gravity-Assisted Magnetic Data," in IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1-5, 2024, Art no. 7503005, doi: 10.1109/LGRS.2024.3382049.
4 Ahmad, W., Ali, H., Shah, Z. et al. A new generative adversarial network for medical images super resolution. Sci Rep 12, 9533 (2022). https://doi.org/10.1038/s41598-022-13658-4
Prosecution Insights