Prosecution Insights
Last updated: April 19, 2026
Application No. 18/521,939

METHOD OF ESTIMATING UNCERTAINTY IN A VISION-BASED TRACKING SYSTEM AND ASSOCIATED APPARATUS AND SYSTEM

Non-Final OA §103
Filed
Nov 28, 2023
Examiner
MEHMOOD, JENNIFER
Art Unit
2664
Tech Center
2600 — Communications
Assignee
The Boeing Company
OA Round
1 (Non-Final)
65%
Grant Probability
Moderate
1-2
OA Rounds
3y 1m
To Grant
95%
With Interview

Examiner Intelligence

Grants 65% of resolved cases
65%
Career Allow Rate
160 granted / 247 resolved
+2.8% vs TC avg
Strong +31% interview lift
Without
With
+30.6%
Interview Lift
resolved cases with interview
Typical timeline
3y 1m
Avg Prosecution
21 currently pending
Career history
268
Total Applications
across all art units

Statute-Specific Performance

§101
2.8%
-37.2% vs TC avg
§103
45.0%
+5.0% vs TC avg
§102
31.9%
-8.1% vs TC avg
§112
17.6%
-22.4% vs TC avg
Black line = Tech Center average estimate • Based on career data from 247 resolved cases

Office Action

§103
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 . Claim Rejections - 35 USC § 103 The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action: A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made. Claim(s) 1-3, 7-13, 15-17 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Leach (EP 4024346) in view of Shi et al. Fast Uncertainty Quantification for Deep Object Pose Estimation With respect to claim 1, Leach teaches a method of estimating the uncertainty in a vision based tracking system , the method comprising: receiving a two dimensional image (see col. 11, line 3) of a portion of a first object (aircraft 110 to be refueled) via a camera (108) on a second object (refueling aircraft 102). Leach teaches establishing/ predicting a set of key-points (para. 9, line 4) of the first object 110 by means of a 2D key-point (object landmark) detection and a 2D to 3D transformation means that determines the 6 degrees of freedom information for each key-point(s) of a fuel receptacle and a tip of the refueling boom (see para. 11, lines 1-6). It appears that the transformation means and the determining means are performed by neural networks as set forth in para. 11, lines 8-12. Leach teaches the computing step as claimed which is recited in para. 11 as previously stated. A 2D to 3D transformation is established by the neural networks. Leach teaches deriving a measure of deviation between 3 D poses. At the bottom of para. 21, Leach teaches using a heatmap pixel values for each key-point, which is a 3D object’s key-point being found at each pixel location of the image. Furthermore, a Kalman filter is used to measure statistical noise and other inaccuracies (deviations as recited in the claim ), and produce estimates. See paras. 20 and 22. Leach teaches controlling a process so that the first object (aircraft to be refueled) and the second object (aircraft refuel platform-102) is refueled in response to a decision operation 738 to determine if the boom tip 106 and the fuel receptacle is within a safety parameter 156. What Leach does not teach is computing a Euclidean norm of the measurement of variation and using it to produce an uncertainty value. Shi teaches computing a distance between the actual pose and an estimated pose. Shi teaches the computation of uncertainty quantification, based on a distribution of the average differences between ground truth of the pose and an estimated pose. A value that has the least of errors is termed a higher value of certainty (See Problem Statement and Metrics at page 3). While Leach does not address uncertainty values in the computation of processing the boom tip with the fuel receptacle, the decision operation 738 performs the similar control processing functions. The Examiner contends that it would have been obvious to one of ordinary skill in the art, to modify the decision operation unit 738 of Leach so that it uses uncertainty values which minimize the errors between estimations, thereby controlling the distance between the boom tip and the fuel receptacle for the purpose of connected the first and second objects. With respect to claim 2, Leach teaches a 2D to 3D transform 620, see para. 49 at col. 13, lines 13-18. See also para. 27, lines 12-16 and para. 45, lines 33-36. The motivation for this rejection is the same as that to claim 1 above. With respect to claim 3, Leach teaches a 3D pose of 6 values for six degrees of freedom. See col. 3,lines 50-57. For example, -X, X, -Y, Y, -Z and Z. Leach teaches deriving a measure of deviation between 3 D poses. At the bottom of para. 21, Leach teaches using a heatmap pixel values for each key-point, which is a 3D object’s key-point being found at each pixel location of the image. Furthermore, a Kalman filter is used to measure statistical noise and other inaccuracies (deviations as recited in the claim ), and produce estimates. See paras. 20 and 22. The motivation for this rejection is the same as that to claim 1. With respect to claim 7, Leach teaches a first object (aircraft 110 to be refueled) to be coupled with second object (refueling aircraft 102) by means of a boom tip 104 and fuel receptacle Leach teaches deriving a measure of deviation between 3 D poses. At the bottom of para. 21, Leach teaches using a heatmap pixel values for each key-point, which is a 3D object’s key-point being found at each pixel location of the image. Furthermore, a Kalman filter is used to measure statistical noise and other inaccuracies (deviations as recited in the claim ), and produce estimates. See paras. 20 and 22. Leach teaches controlling a process so that the first object (aircraft to be refueled) and the second object (aircraft refuel platform-102) is refueled in response to a decision operation 738 to determine if the boom tip 106 and the fuel receptacle is within a safety parameter 156. If the safety parameter 156 is within range then engaging will occur and will not be engaged when the safety parameter 156 is outside the threshold value. See para. 49 regarding the engagement of the boom tip 106 and the fuel receptacle is within the safety parameter 156, see para. 49, lines 1-6. While Leach does not address uncertainty values in the computation of processing the boom tip with the fuel receptacle, the decision operation 738 performs the similar control processing functions. The Examiner contends that it would have been obvious to one of ordinary skill in the art, to modify the decision operation unit 738 of Leach so that it uses uncertainty values which minimize the errors between estimations, thereby controlling the distance between the boom tip and the fuel receptacle for the purpose of connected the first and second objects. The motivation for this rejection is the same as that to claim 1. With respect to claim 8, at para. 49, Leach teaches the control of the engagement between the boom 106 and fuel receptacle. See also the first four lines of para. 50. Leach teaches controlling a process so that the first object (aircraft to be refueled) and the second object (aircraft refuel platform-102) is refueled in response to a decision operation 738 to determine if the boom tip 106 and the fuel receptacle is within a safety parameter 156. See col. 1, lines 45-48 regarding automated control. See also para. 17, last 8 lines. With respect to claim 9, Leach teaches using manual control of the refueling engagement process. See para. 1, lines 1-9, para. 2 (entirety). With respect to claim 10, Leach teaches a 2D image of the landmark key- points of the second object (visualization of the boom tip). Leach teaches predicting other key points such as the wingtip para. 21, lines 15-16, and fiducial marks 118 (see para. 18). With respect to claim 11, Leach teaches the first object is a receiver aircraft 110 and the second object is a tanker aircraft 102 and the process is a refueling process, see paragraph 1, lines 1-5; para. 4, lines 1-6 and para. 9, lines 1-4. The motivation for the rejection is the same as that to claim 1. With respect to claim 12, Leach teaches a vision based tracking system comprising: one or more processors 904; a non-transitory computer readable medium 902 for storing instructions 902a. Leach teaches receiving a two dimensional image (see col. 11, line 3) of a portion of a first object (aircraft 110 to be refueled) via a camera (108) on a second object (refueling aircraft 102). Leach teaches establishing/ predicting a set of key-points (para. 9, line 4) of the first object 110 by means of a 2D key-point (object landmark) detection and a 2D to 3D transformation means that determines the 6 degrees of freedom information for each key-point(s) of a fuel receptacle and a tip of the refueling boom (see para. 11, lines 1-6). It appears that the transformation means and the determining means are performed by neural networks as set forth in para. 11, lines 8-12. Leach teaches the computing step as claimed which is recited in para. 11 as previously stated. A 2D to 3D transformation is established by the neural networks. Leach teaches deriving a measure of deviation between 3 D poses. At the bottom of para. 21, Leach teaches using a heatmap pixel values for each key-point, which is a 3D object’s key-point being found at each pixel location of the image. Furthermore, a Kalman filter is used to measure statistical noise and other inaccuracies (deviations as recited in the claim ), and produce estimates. See paras. 20 and 22. Leach teaches controlling a process so that the first object (aircraft to be refueled) and the second object (aircraft refuel platform-102) is refueled in response to a decision operation 738 to determine if the boom tip 106 and the fuel receptacle is within a safety parameter 156. What Leach does not teach is computing a Euclidean norm of the measurement of variation and using it to produce an uncertainty value. Shi teaches computing a distance between the actual pose and an estimated pose. Shi teaches the computation of uncertainty quantification, based on a distribution of the average differences between ground truth of the pose and an estimated pose. A value that has the least of errors is termed a higher value of certainty (See Problem Statement and Metrics at page 3). While Leach does not address uncertainty values in the computation of processing the boom tip with the fuel receptacle, the decision operation 738 performs the similar control processing functions. The Examiner contends that it would have been obvious to one of ordinary skill in the art, to modify the decision operation unit 738 of Leach so that it uses uncertainty values which minimize the errors between estimations, thereby controlling the distance between the boom tip and the fuel receptacle for the purpose of connected the first and second objects. With respect to claim 13, Leach teaches a 2D to 3D transform 620, see para. 49 at col. 13, lines 13-18. See also para. 27, lines 12-16 and para. 45, lines 33-36. The motivation for this rejection is the same as that to claim 12 above. With respect to claim 15, Leach teaches one or more processors 904; a non-transitory computer readable medium 902 for storing instructions 902a. Leach teaches a first object (aircraft 110 to be refueled) to be coupled with second object (refueling aircraft 102) by means of a boom tip 104 and fuel receptacle. The motivation for this rejection is the same as that to claim 12. Leach teaches deriving a measure of deviation between 3 D poses. At the bottom of para. 21, Leach teaches using a heatmap pixel values for each key-point, which is a 3D object’s key-point being found at each pixel location of the image. Furthermore, a Kalman filter is used to measure statistical noise and other inaccuracies (deviations as recited in the claim ), and produce estimates. See paras. 20 and 22. Leach teaches controlling a process so that the first object (aircraft to be refueled) and the second object (aircraft refuel platform-102) is refueled in response to a decision operation 738 to determine if the boom tip 106 and the fuel receptacle is within a safety parameter 156. If the safety parameter 156 is within range then engaging will occur and will not be engaged when the safety parameter 156 is outside the threshold value. See para. 49 regarding the engagement of the boom tip 106 and the fuel receptacle is within the safety parameter 156, see para. 49, lines 1-6. While Leach does not address uncertainty values in the computation of processing the boom tip with the fuel receptacle, the decision operation 738 performs the similar control processing functions. The Examiner contends that it would have been obvious to one of ordinary skill in the art, to modify the decision operation unit 738 of Leach so that it uses uncertainty values which minimize the errors between estimations, thereby controlling the distance between the boom tip and the fuel receptacle for the purpose of connected the first and second objects. With respect to claim 16, Leach teaches a vision based tracking system, comprising: a camera 108 configured to generate a 2D image of a first portion the first object is a receiver aircraft 110 and the second object is a tanker aircraft 102 and the process is a refueling process, see paragraph 1, lines 1-5; para. 4, lines 1-6 and para. 9, lines 1-4. Leach teaches one or more processors 904; a non-transitory computer readable medium 902 for storing instructions 902a. Leach teaches receiving a two dimensional image (see col. 11, line 3) of a portion of a first object (aircraft 110 to be refueled) via a camera (108) on a second object (refueling aircraft 102). Leach teaches establishing/ predicting a set of key-points (para. 9, line 4) of the first object 110 by means of a 2D key-point (object landmark) detection and a 2D to 3D transformation means that determines the 6 degrees of freedom information for each key-point(s) of a fuel receptacle and a tip of the refueling boom (see para. 11, lines 1-6). It appears that the transformation means and the determining means are performed by neural networks as set forth in para. 11, lines 8-12. Leach teaches the computing step as claimed which is recited in para. 11 as previously stated. A 2D to 3D transformation is established by the neural networks. Leach teaches deriving a measure of deviation between 3D poses. At the bottom of para. 21, Leach teaches using a heatmap pixel values for each key-point, which is a 3D object’s key-point being found at each pixel location of the image. Furthermore, a Kalman filter is used to measure statistical noise and other inaccuracies (deviations as recited in the claim ), and produce estimates. See paras. 20 and 22. Leach teaches controlling a process so that the first object (aircraft to be refueled) and the second object (aircraft refuel platform-102) is refueled in response to a decision operation 738 to determine if the boom tip 106 and the fuel receptacle is within a safety parameter 156. What Leach does not teach is computing a Euclidean norm of the measurement of variation and using it to produce an uncertainty value. Shi teaches computing a distance between the actual pose and an estimated pose. Shi teaches the computation of uncertainty quantification, based on a distribution of the average differences between ground truth of the pose and an estimated pose. A value that has the least of errors is termed a higher value of certainty (See Problem Statement and Metrics at page 3). While Leach does not address uncertainty values in the computation of processing the boom tip with the fuel receptacle, the decision operation 738 performs the similar control processing functions. The Examiner contends that it would have been obvious to one of ordinary skill in the art, to modify the decision operation unit 738 of Leach so that it uses uncertainty values which minimize the errors between estimations, thereby controlling the distance between the boom tip and the fuel receptacle for the purpose of connected the first and second objects. With respect to claim 17, Leach teaches a 2D to 3D transform 620, see para. 49 at col. 13, lines 13-18. See also para. 27, lines 12-16 and para. 45, lines 33-36. The motivation for this rejection is the same as that to claim 16. With respect to claim 20, Leach teaches a process of engagement with a first object (aircraft 110 to be refueled) to be coupled with second object (refueling aircraft 102) by means of a boom tip 104 and fuel receptacle Leach teaches deriving a measure of deviation between 3 D poses. At the bottom of para. 21, Leach teaches using a heatmap pixel values for each key-point, which is a 3D object’s key-point being found at each pixel location of the image. Furthermore, a Kalman filter is used to measure statistical noise and other inaccuracies (deviations as recited in the claim ), and produce estimates. See paras. 20 and 22. Leach teaches controlling a process so that the first object (aircraft to be refueled) and the second object (aircraft refuel platform-102) is refueled in response to a decision operation 738 to determine if the boom tip 106 and the fuel receptacle is within a safety parameter 156. If the safety parameter 156 is within range then engaging will occur and will not be engaged when the safety parameter 156 is outside the threshold value. See para. 49 regarding the engagement of the boom tip 106 and the fuel receptacle is within the safety parameter 156, see para. 49, lines 1-6. While Leach does not address uncertainty values in the computation of processing the boom tip with the fuel receptacle, the decision operation 738 performs the similar control processing functions. The Examiner contends that it would have been obvious to one of ordinary skill in the art, to modify the decision operation unit 738 of Leach so that it uses uncertainty values which minimize the errors between estimations, thereby controlling the distance between the boom tip and the fuel receptacle for the purpose of connected the first and second objects. Claim(s) 4, 5, 6, 14, 18 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Leach (EP 4024346) in view of Shi et al. Fast Uncertainty Quantification for Deep Object Pose Estimation further in view of KSR v. Teleflex 550 U.S. 398 (2007) With respect to claim 4, Leach teaches a multiple key point detectors of a 2D key-point (object landmark) detection and a 2D to 3D transformation means which detects multiple key-points. It appears that the multiple means for determining multiple key-points are multi-stage pose estimation pipelines which use real-time deep-learning algorithms such as deep neural networks, see col. 4, lines 5-9. Leach specifically mentions identification of at least three key-points, namely, the boom tip, wing edge and the fiduciary mark 118. The examiner contends that the detector 310 is comprised of at least one neural network but is structured to identify different structures corresponding with the identification of multiple key-points, such as the wingtip and fuselage. In the alternative, the Examiner contends that it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to try any number of different detectors 310, each for identifying a section of the aircraft t having identical architecture and receiving the same type of training with random valued weights which would have been suggested by one of ordinary skill in the art seeking a specified result to minimize error in estimation. With respect to claim 5, Leach teaches an aircraft key-point detector 310. Leach also teaches that the detector is trained by a key-point model trainer 352, see para. 6, lines 40-45. The examiner contends that the detector 310 is comprised of at least one neural network but is structured to identify different structures corresponding with the identification of multiple key-points, such as the wingtip and fuselage. In the alternative, the Examiner contends that it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to try the use of different detectors 310, each for identifying a section of the aircraft to be refueled and each having identical architecture and receiving the same type of training with random valued weights which would have been suggested by one of ordinary skill in the art seeking a specified result to minimize error in estimation. The motivation for this rejection is the same as that to claim 1. With respect to claim 6, Leach teaches a data pre-processor component 340 that train images. At para. 26 beginning at line 14, the loss that is minimized during training is the pixel-wise mean-squared -error between the heat map and the ground truth heat map. This mean-squared-error is the computation of the standard deviation. The training images occur in 3D as set forth in para. 25, beginning at line 4. The motivation for this rejection is the same as that to claim 5 depending from claim 1. With respect to claim 14, Leach teaches one or more processors 904; a non-transitory computer readable medium 902 for storing instructions 902a. Leach teaches an aircraft key-point detector 310. Leach also teaches that the detector is trained by a key-point model trainer 352, see para. 6, lines 40-45. The examiner contends that the detector 310 is comprised of at least one neural network but is structured to identify different structures corresponding with the identification of multiple key-points, such as the wingtip and fuselage. In the alternative, the Examiner contends that it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to try the use of different detectors 310, each for identifying a section of the aircraft to be refueled and each having identical architecture and receiving the same type of training with random valued weights which would have been suggested by one of ordinary skill in the art seeking a specified result to minimize error in estimation. With respect to claim 18, Leach teaches software code via instructions (902a) implemented by one or more processors 904 for training key-point detectors. Leach teaches an aircraft key-point detector 310. Leach also teaches that the detector is trained by a key-point model trainer 352, see para. 6, lines 40-45. The examiner contends that the detector 310 is comprised of at least one neural network but is structured to identify different structures corresponding with the identification of multiple key-points, such as the wingtip and fuselage. In the alternative, the Examiner contends that it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to try the use of different detectors 310, each for identifying a section of the aircraft to be refueled and each having identical architecture and receiving the same type of training with random valued weights which would have been suggested by one of ordinary skill in the art seeking a specified result to minimize error in estimation. The motivation for this rejection is the same as that to claim 16. With respect to claim 19, Leach teaches a data pre-processor component 340 that train images. At para. 26 beginning at line 14, the loss that is minimized during training is the pixel-wise mean-squared -error between the heat map and the ground truth heat map. This mean-squared-error is the computation of the standard deviation. The training images occur in 3D as set forth in para. 25, beginning at line 4. The motivation for this rejection is the same as that to claim 18. Any inquiry concerning this communication or earlier communications from the examiner should be directed to JEROME GRANT II whose telephone number is (571)272-7463. The examiner can normally be reached M-F 9:00 a.m. - 5:00 p.m.. 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, Nay Maung can be reached at 571-272-7882. 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. /JEROME GRANT II/Primary Examiner, Art Unit 2664
Read full office action

Prosecution Timeline

Nov 28, 2023
Application Filed
Jan 09, 2026
Non-Final Rejection — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12572774
NEURAL NETWORK PROCESSOR AND METHOD OF NEURAL NETWORK PROCESSING
2y 5m to grant Granted Mar 10, 2026
Patent 10269295
ORGANIC LIGHT EMITTING DISPLAY DEVICE AND DRIVING METHOD THEREOF
2y 5m to grant Granted Apr 23, 2019
Patent 9245189
OBJECT APPEARANCE FREQUENCY ESTIMATING APPARATUS
2y 5m to grant Granted Jan 26, 2016
Patent 8344909
METHOD AND SYSTEM FOR COLLECTING TRAFFIC DATA, MONITORING TRAFFIC, AND AUTOMATED ENFORCEMENT AT A CENTRALIZED STATION
2y 5m to grant Granted Jan 01, 2013
Patent 8294567
METHOD AND SYSTEM FOR FIRE DETECTION
2y 5m to grant Granted Oct 23, 2012
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
65%
Grant Probability
95%
With Interview (+30.6%)
3y 1m
Median Time to Grant
Low
PTA Risk
Based on 247 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month