DETAILED ACTION
Response to Amendment
Applicant's submission filed on July 30, 2026 has been entered.
Claims 1, 3-5, 8, and 13-16 are amended.
Claim 2 and 7 are cancelled.
Claim 17 is new.
Claim 1, 3-6, and 8-17 are pending this application.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3, 6, and 8-17 are rejected under 35 U.S.C. 103 as being unpatentable over Werner et al (US 2020/0049837 A1) in view of Sun et al (IEEE, 2020).
Regarding Claim 1, Werner teaches a computer-implemented method of training a machine learnable model to correct an output of a global satellite navigation receiver, the method comprising [0048, 0053]:
obtaining geolocation data which is generated by a global satellite navigation receiver, wherein an instance of the geolocation data represents a computed geolocation by the global satellite navigation receiver, wherein the computed geolocation is obtained by solving a set of navigation equations [0048-0051 for high precision location estimates with training data];
obtaining auxiliary data which is generated by the global satellite navigation receiver in addition to the geolocation data, wherein an instance of the auxiliary data comprises, for a respective satellite [0049-0053 for using azimuth, elevation and residual error data]:
a residual associated with the satellite, which residual is an error term resulting from a computational solution to the set of navigation equations [0053-0055];
and satellite direction information indicative of a direction of the satellite relative to the global satellite navigation receiver [0048, 0051];
obtaining reference data for the global satellite navigation receiver, wherein an instance of the reference data represents a reference geolocation of the global satellite navigation receiver [0055];
training the machine learnable model by [0048-0051]:
for respective instances of the geolocation data and the reference data, determining a positioning error as a difference between the computed geolocation and the reference geolocation [0018, 0057-0058];
wherein the positioning error is a 2D or 3D positioning-error correction term which, when, added to or subtracted from the computed geolocation, yields or approximates, the reference geolocation [0068 for a more accurate indication of error and/or uncertainty than the uncertainty parameters with 0070 for machine learning model may indicate a revised (add/subtract) measurement for the location estimation];
in a training step, training the machine learnable model using the auxiliary data to predict the positioning error (PE) based on the residual and the satellite direction information [0055-0058];
outputting a data representation of a machine learned model [0055-0058 for facilitating device location (means to output data)].
Werner fails to explicitly teach outputting a data representation of a machine learned model representing a trained version of the machine learnable model.
Sun has two variations of the algorithm are proposed to improve positioning accuracy (page 7065, abstract) and teaches outputting a data representation of a machine learned model (TM) representing a trained version of the machine learnable model [page 7069, Section II D and equations 8-13].
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention for modifying the position correction techniques, as disclosed by Werner, further including the machine learning calculations as taught by Sun for the purpose to predict the pseudorange errors for each observed satellite (Sun, page 7069, right column, last two paragraphs).
Regarding Claim 3, Werner teaches the satellite direction information comprises, for a respective satellite, an elevation and an azimuth of the satellite in the sky at the computed geolocation [0049-0051].
Regarding Claim 6, Werner teaches the training is further based on at least one of: a carrier-to-noise ratio of a radio signal received from a satellite; a quality indicator associated with the radio signal; and a tracking indicator indicating presence and/or quality of signal tracking; a multipath indicator indicating multipath reception; an estimate of measurement noise; an environment type indicating a type of environment at the geolocation of the global satellite navigation receiver; and the geolocation, or a quantized version of the geolocation, of the global satellite navigation receiver [0051].
Regarding Claim 8, Werner teaches a computer-implemented method of correcting an output of a global satellite navigation receiver, the method comprising [0048]:
obtaining an instance of geolocation data which is generated by a global satellite navigation receiver, wherein the instance of the geolocation data represents a computed geolocation by the global satellite navigation receiver, wherein the computed geolocation is obtained by solving a set of navigation equations [0048-0051 for high precision location estimates with training data];
obtaining an instance of auxiliary data which is generated by the global satellite navigation receiver in addition to the instance of geolocation data, wherein the instance of the auxiliary data comprises, for a respective satellite [0049-0053 for using azimuth, elevation and residual error data]:
a residual associated with a satellite, which residual is an error term resulting from a computational solution to the set of navigation equations [0053-0055];
satellite direction information indicative of a direction of the satellite relative to the computed geolocation n [0048, 0051];
accessing a machine learned model which is trained to predict a positioning error based on a residual and satellite direction information which are provided during training, wherein the positioning error is a difference between a computed geolocation and a reference geolocation provided during training [0055-0058 for facilitating device location];
wherein the positioning error is a difference between a computed geolocation provided during training and a reference geolocation provided during training and is determined as a 2D or 3D positioning error correction term which when added to or subtracted from the computed geolocation provided during training, yields or approximates the reference geolocation provided during training [0068 for a more accurate indication of error and/or uncertainty than the uncertainty parameters with 0070 for machine learning model may indicate a revised (add/subtract) measurement for the location estimation];
using the machine learned model, predicting the positioning error for the computed geolocation based on the residual and the satellite direction information to obtain a predicted positioning error [0055-0058];
and correcting the computed geolocation [0021, 0070 for indicate a revised measurement for the location estimation included with the GNSS receiver data] by adding the predicted position error to, or subtracting the predicted positioning error from, the computed geolocation.
Werner fails to explicitly teach correcting the computed geolocation to account for the predicted positioning error.
Sun has two variations of the algorithm are proposed to improve positioning accuracy (page 7065, abstract) and teaches correcting the computed geolocation to account for the predicted positioning error [page 7069, Section II E, equation (1) and page 7070 right column first two paragraph equation (14)].
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention for modifying the position correction techniques, as disclosed by Werner, further including the machine learning calculations as taught by Sun for the purpose to predict the pseudorange errors for each observed satellite (Sun, page 7069, right column, last two paragraphs).
Regarding Claim 9, Werner teaches the method as a continuous learning step [0037-0039].
Regarding Claim 10, Werner teaches obtaining a reference geolocation for the continuous learning step by at least one of: enabling a user to manually enter a reference geolocation; and - sensing the reference geolocation in separation of the use of global satellite navigation, for example using a beacon [0105 for input device interface and laptop (means for manual entry)].
Regarding Claim 11, Werner teaches computer-readable medium comprising non-transitory data representing a computer program, the computer program comprising instructions for causing a processor system to perform the method [0105].
Regarding Claim 12, Werner teaches a computer-readable medium comprising non- transitory data (610) representing a machine learned model obtainable by the method [0034-0036].
Regarding Claim 13, Werner teaches a training system for training a machine learnable model to correct an output of a global satellite navigation receiver, the training system comprising [0048]:
an input interface subsystem for obtaining [0065 for user devices and input interfaces]:
geolocation data which is generated by a global satellite navigation receiver, wherein an instance of the geolocation data represents a computed geolocation by the global satellite navigation receiver, wherein the computed geolocation is obtained by solving a set of navigation equations [0048-0051 for high precision location estimates with training data]; and
auxiliary data which is generated by the global satellite navigation receiver in addition to the geolocation data, wherein an instance of the auxiliary data comprises, for a respective satellite [0049-0053 for using azimuth, elevation and residual error data]: and
a residual associated with a satellite, which residual is an error term resulting from a computational solution to the set of navigation equations [0053-0055];
satellite direction information indicative of a direction of the satellite relative to the global satellite navigation receiver [0048, 0051];
reference data for the global satellite navigation receiver, wherein an instance of the reference data represents a reference geolocation of the global satellite navigation receiver [0054-0055];
a processor subsystem configured to train the machine learnable model (310) by [0055-0058]:
for respective instances of the geolocation data and the reference data, determining a positioning error as a difference between a computed geolocation and a reference geolocation [0057-0059];
wherein the positioning error is a 2D or 3D positioning-error correction term, which when added to or subtracted from the computed geolocation, yields or approximates the reference geolocation [0068 for a more accurate indication of error and/or uncertainty than the uncertainty parameters with 0070 for machine learning model may indicate a revised (add/subtract) measurement for the location estimation];
in a training step, training the machine learnable model using the auxiliary data to predict the positioning error based on the residual and the satellite direction information [0052 using training, testing, tracking position (auxiliary) data].
Werner fails to explicitly teach output interface subsystem for outputting a data representation of a machine learned model representing a trained version of the machine learnable model.
Sun has two variations of the algorithm are proposed to improve positioning accuracy (page 7065, abstract) and teaches output interface subsystem for outputting a data representation of a machine learned model representing a trained version of the machine learnable model [page 7069, Section II D and equations 8-13].
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention for modifying the position correction techniques, as disclosed by Werner, further including the machine learning calculations as taught by Sun for the purpose to predict the pseudorange errors for each observed satellite (Sun, page 7069, right column, last two paragraphs).
Regarding Claim 14, Werner teaches a correction system for correcting an output of a global satellite navigation receiver, the correction system comprising [0048]:
an input interface subsystem for obtaining [0065 for inputting using user devices]:
an instance of geolocation data which is generated by a global satellite navigation receiver, wherein the instance of the geolocation data represents a computed geolocation by the global satellite navigation receiver, wherein the computed geolocation is obtained by solving a set of navigation equations [0048-0051 for high precision location estimates with training data];
an instance of auxiliary data which is generated by the global satellite navigation receiver in addition to the instance of geolocation data, wherein the instance of the auxiliary data comprises, for a respective satellite [0049-0053 for using azimuth, elevation and residual error data]: and
a residual associated with a satellite, which residual is an error term resulting from a computational solution to the set of navigation equations [0053-0055];
and satellite direction information indicative of a direction of the satellite relative to the computed geolocation [0048, 0051];
a machine learned model which is trained to predict a positioning error based on a residual and satellite direction information which are provided during training, wherein the positioning error is a difference between a computed geolocation provided during training and a reference geolocation provided during training [0055-0058];
and is determined as a 2D or 3D positioning error correction term which, when added to or subtracted from the computed geolocation provided during training, yields or approximates the reference geolocation provided during the training [0068 for a more accurate indication of error and/or uncertainty than the uncertainty parameters with 0070 for machine learning model may indicate a revised (add/subtract) measurement for the location estimation];
a processor subsystem configured to [0055-0058]:
using the machine learned model, predict the positioning error for the computed geolocation based on the residual and the satellite direction information to obtain a predicted positioning error [0053-0055];
correct the computed geolocation [0021, 0048-0051, 0070 for the output from the machine learning model may replace or otherwise supplement the location estimation].
Werner fails to explicitly teach correct the computed geolocation to account for the predicted positioning error by adding the predicted positioning error to or subtracting the predicted positioning error from the computed geolocation.
Sun has two variations of the algorithm are proposed to improve positioning accuracy (page 7065, abstract) and teaches correct the computed geolocation to account for the predicted positioning error [page 7069, Section II E, equation (1) and page 7070 right column first two paragraph equation (14)].
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention for modifying the position correction techniques, as disclosed by Werner, further including the machine learning calculations as taught by Sun for the purpose to predict the pseudorange errors for each observed satellite (Sun, page 7069, right column, last two paragraphs).
Regarding Claim 15, Werner teaches device comprising a global satellite navigation receiver and the correction system to correct an output of the global satellite navigation receiver [0065-0066].
Regarding Claim 16, Werner teaches the training system as a continuous-learning subsystem [0037-0039].
Regarding Claim 17, Werner teaches the residual is one of: a pseudorange residual; or an innovation residual obtained from a Kalman filtering performed by the global satellite navigation receiver [0056 for using a Kalman filter].
Claims 4-5 are rejected under 35 U.S.C. 103 as being unpatentable over Werner et al (US 2020/0049837 A1) in view of Sun et al (IEEE, 2020) as applied to claim 1 above, and further in view of Judd (US 10,884,132 B1).
Regarding Claim 4, Werner fails to explicitly teach the method comprises representing the elevation, the azimuth and the residual as a data tuple representing a spherical coordinate in a spherical coordinate system.
Judd has beacon-based Precision Navigation and Timing (abstract) and teaches representing the elevation, the azimuth and the residual as a data tuple representing a spherical coordinate in a spherical coordinate system [col 11, lines 10-25].
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention for modifying the position correction techniques, as disclosed by Werner, further including the coordinate calculations as taught by Judd for the purpose to calculate its position accurately without having perfect ephemerides (Judd, col 11, lines 15-25).
Regarding Claim 5, Werner teaches converting the spherical coordinate to a cartesian coordinate in an earth-centered, earth-fixed coordinate system, wherein the cartesian coordinate is used in the training of the machine learnable model.
Judd has beacon-based Precision Navigation and Timing (abstract) and teaches the spherical coordinate to a cartesian coordinate in an earth-centered, earth-fixed coordinate system, wherein the cartesian coordinate is used in the training of the machine learnable mode [col 9, lines 20-35 and col 11, lines 10-25].
It would have been obvious to a person of ordinary skill in the art before the effective filling date of the applicant’s invention for modifying the position correction techniques, as disclosed by Werner, further including the coordinate calculations as taught by Judd for the purpose to calculate its position accurately without having perfect ephemerides (Judd, col 11, lines 15-25).
Response to Arguments
Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references.
On page 4, second paragraph of applicant’s arguments, the applicant states that Werner nor Sun teach correction as a post filter using information available at the output of the GNSS receiver. The examiner thanks the applicant for the amendments and respectfully disagrees, Werner teaches machine learning model can be used to replace and/or supplement subsequent position estimates [Werner, 0022] therefore the machine learning model operates on the receiver’s already computed output data PVT as an external input to a downstream Kalman filter [Werner, 0067].
On page 4, third paragraph of applicant’s arguments, the applicant states that Werner’s nor Sun suggest this use of the positioning correction vector. The examiner respectfully disagrees: Werner’s teaches provide more accurate location error/uncertainty (e.g., based on the residual error determined from the GNSS position estimates (same use of the position correction vector) [Werner, 0058].
On page 4, last paragraph of applicant’s arguments, the applicant states that Werner’s fails to disclose the claimed model output. The examiner respectfully disagrees: Werner teaches a revised measurement for the location estimation included with the GNSS receiver data (a correction that directly replaces/adjusts the computed geolocation towards the reference geolocation) [Werner, 0070].
On page 5, second paragraph of applicant’s arguments, the applicant that Werner fails to disclose a positioning correction vector. The examiner respectfully disagrees: Werner teaches accurate location error/uncertainty e.g., based on the residual error determined from the GNSS position estimates and the reference device position estimates (the revised coordinate output is nothing more than the computed geolocation with that learned residual error vector applied by definition) [Werner, 0058].
On page 5, third paragraph of applicant’s arguments, the applicant that Sun fails to cure the deficiencies of Werner. The examiner respectfully disagrees: Sun teaches using a machine learning model to predict the pseudorange errors and correcting the errors confirming the models output is explicitly an error/correction term applied to the computed position [Sun, abstract].
Conclusion
THIS ACTION IS MADE FINAL. 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 SAMARINA MAKHDOOM whose telephone number is (703)756-1044. The examiner can normally be reached Monday – Thursdays from 8:30 to 5:30 pm eastern 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.
/SAMARINA MAKHDOOM/
Examiner, Art Unit 3648
Prosecution Insights