IP Library Granted Patent US 12,729,010
Granted Patent B2
US 12,729,010 · App. 18/525,318 · Granted Sep 8, 2026

Systems and methods for calculating refueling tanker boom 3D position for aerial refueling

Inventors: Fan Hin Hung (Los Angeles, CA); Deepak Khosla (Camarillo, CA); Shawn Chamberlain (Federal Way, WA); Daniel O'Shea (Seattle, WA); Neale Ratzlaff (Los Angeles, CA); Tameez Latib (Calabasas, CA); Haden Smith (Guyton, GA); Leon Nguyen (Santa Ana, CA)
Assignee: The Boeing Company
B64D43/00B64D39/06G05D1/104
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,729,010
App. No.
18/525,318
Granted
Sep 8, 2026
Kind
B2
Abstract

Disclosed herein is methods, systems, and aircraft for performing image analysis for aiding refueling operations. A tanker aircraft includes a camera, a refueling boom, a camera configured to generate a two-dimensional (2D) image of the refueling boom, a processor, and non-transitory computer readable storage media storing code. The code is executable by the processor to perform operations including receiving the two-dimensional (2D) image from the camera, determining 2D keypoints of the refueling boom located within the 2D image based on a predefined point model of the refueling boom, determining a 6 degree-of-freedom (6DOF) pose using the 2D keypoints and the corresponding three-dimensional (3D) space 3D keypoints, optimizing 3D keypoints associated with moveable components of the refueling boom in response to a plurality of boom control parameters to produce optimized 3D keypoints, and estimating a position of a tip of the refueling boom based on the 6DOF pose.

Claims (53)

1 . A method comprising:

receiving a two-dimensional (2D) image from a camera of a tanker aircraft;

determining 2D keypoints of a refueling boom located within the 2D image based on a predefined point model of a refueling boom;

determining a 6 degree-of-freedom (6DOF) pose using the determined 2D keypoints and corresponding three-dimensional (3D) space keypoints;

optimizing 3D keypoints associated with moveable components of the refueling boom by iteratively solving for a plurality of boom control parameters for the moveable components, based on a difference between the determined 2D keypoints and projected 2D keypoints generated by projecting the 3D keypoints onto the 2D image using the determined 6DOF pose to produce optimized 3D keypoints such that the projected 2D keypoints substantially align with the determined 2D keypoints; and

estimating a position of the refueling boom based on the 6DOF pose and the optimized 3D keypoints.

2 . The method of claim 1 , wherein determining the 6DOF pose comprises performing a perspective-n-point algorithm using the determined 2D keypoints and the 3D keypoints to produce the 6DOF pose.

3 . The method of claim 1 , further comprising:

receiving a boom tip extension value; and

estimating a position of a tip of the refueling boom based on the boom tip extension value.

4 . The method of claim 1 , wherein the boom control parameters comprise at least one angle between two components of the refueling boom, wherein at least one of the two components comprises a component that is moveable relative to a main body of the refueling boom.

5 . The method of claim 1 , wherein:

generating the projected 2D keypoints is based on the plurality of boom control parameters for the moveable components of the refueling boom;

the method further comprises:

determining the 6DOF pose prior to iteratively solving for the plurality of boom control parameters; and

optimizing the 3D keypoints associated with moveable components of the refueling boom without re-determining the 6DOF pose.

6 . The method of claim 5 , wherein optimizing is performed using an initial value.

7 . The method of claim 1 , further comprising sending the position of the refueling boom to an output device.

8 . The method of claim 7 , wherein the output device comprises an automated refueling system, a pilot director light system, or a boom operator interface.

9 . A tanker aircraft comprising:

a refueling boom;

a camera configured to generate a two-dimensional (2D) image of the refueling boom;

a processor; and

non-transitory computer readable storage media storing code, the code being executable by the processor to perform operations comprising:

receiving the two-dimensional (2D) image from the camera;

determining 2D keypoints of the refueling boom located within the 2D image based on a predefined point model of the refueling boom;

determining a 6 degree-of-freedom (6DOF) pose using the determined 2D keypoints and corresponding three-dimensional (3D) space keypoints;

optimizing 3D keypoints associated with moveable components of the refueling boom by iteratively solving for a plurality of boom control parameters for the moveable components, based on a difference between the determined 2D keypoints and projected 2D keypoints generated by projecting the 3D keypoints onto the 2D image using the determined 6DOF pose to produce optimized 3D keypoints such that the projected 2D keypoints substantially align with the determined 2D keypoints; and

estimating a position of a tip of the refueling boom based on the 6DOF pose and on the optimized 3D keypoints.

10 . The tanker aircraft of claim 9 , further comprising transforming the determined 2D keypoints to 3D space by performing a perspective-n-point algorithm using the determined 2D keypoints and the 3D keypoints to produce the 6DOF pose.

11 . The tanker aircraft of claim 9 , wherein:

the tanker aircraft further comprises a boom tip sensor; and

estimating the position of the tip of the refueling boom comprises:

receiving a boom tip extension value from the boom tip sensor; and

estimating the position of the tip of the refueling boom based on the boom tip extension value.

12 . The tanker aircraft of claim 9 , wherein the boom control parameters comprise at least one angle between two components of the refueling boom, wherein at least one of the two components comprises a component that is moveable relative to a main body of the refueling boom.

13 . The tanker aircraft of claim 12 , wherein optimizing comprises optimizing for a predefined amount of time or until a result is within a predefined range.

14 . The tanker aircraft of claim 13 , wherein optimizing is performed using an initial value.

15 . The tanker aircraft of claim 9 , wherein:

the tanker aircraft further comprises an output device; and

the processor further performs an operation of sending the position of the tip of the refueling boom to the output device.

16 . The tanker aircraft of claim 15 , wherein the output device comprises an automated refueling system, a pilot director light system, or a boom operator interface.

17 . A refueling system comprising:

a processor; and

non-transitory computer readable storage media storing code, the code being executable by the processor to perform operations comprising:

receiving a two-dimensional (2D) image from a camera;

determining 2D keypoints of a refueling boom located within the 2D image based on a predefined point model of the refueling boom;

determining a 6 degree-of-freedom (6DOF) pose using the determined 2D keypoints and corresponding three-dimensional (3D) keypoints;

optimizing 3D keypoints associated with moveable components of the refueling boom by iteratively solving for a plurality of boom control parameters for the moveable components, based on a difference between the determined 2D keypoints and projected 2D keypoints generated by projecting the 3D keypoints onto the 2D image using the determined 6DOF pose to produce optimized 3D keypoints such that the projected 2D keypoints substantially align with the determined 2D keypoints; and

estimating a position of a tip of the refueling boom based on the 6DOF pose and on the optimized 3D keypoints.

18 . The refueling system of claim 17 , further comprising transforming the 2D keypoints to 3D space by performing a perspective-n-point algorithm using the determined 2D keypoints and 3D keypoints to produce the 6DOF pose.

19 . The refueling system of claim 17 , wherein the boom control parameters comprise at least one angle between two components of the refueling boom, wherein at least one of the two components comprises a component that is moveable relative to a main body of the refueling boom.

20 . The refueling system of claim 19 , wherein optimizing comprises optimizing for a predefined amount of time or until a result is within a predefined range responsive to an initial value.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 30, 2023
From: HUNG, FAN HIN; KHOSLA, DEEPAK; CHAMBERLAIN, SHAWN; O'SHEA, DANIEL; RATZLAFF, NEALE; LATIB, TAMEEZ; SMITH, HADEN; NGUYEN, LEON
To: THE BOEING COMPANY
Reel/Frame 065725/0534 →
Continuity (1)
Related Publication 20250178741A1 · Jun 5, 2025
References Cited (122)
US 7980512B1 · Speer · 2011 [cited by examiner]
US 8854433B1 · Rafii · 2014 [cited by applicant]
US 8994723B2 · Drost et al. · 2015 [cited by applicant]
US 9150310B1 · Bray et al. · 2015 [cited by applicant]
US 10565731B1 · Reddy · 2020 [cited by applicant]
US 10909715B1 · Boggs · 2021 [cited by applicant]
US 10929654B2 · Iqbal · 2021 [cited by applicant]
US 10937189B2 · Li et al. · 2021 [cited by applicant]
US 11254440B2 · Ropers · 2022 [cited by applicant]
US 11459116B2 · Kyono et al. · 2022 [cited by applicant]
US 11748913B2 · Ali et al. · 2023 [cited by applicant]
US 11827203B2 · Chakravarty et al. · 2023 [cited by applicant]
US 11880503B1 · Haentjens · 2024 [cited by applicant]
US 12139271B2 · Khosla · 2024 [cited by applicant]
US 20070023575A1 · von Thal · 2007 [cited by examiner]
US 20170073080A1 · Hughes · 2017 [cited by examiner]
US 20180173839A1 · Fang · 2018 [cited by applicant]
US 20180178924A1 · Zomeño Rodríguez · 2018 [cited by examiner]
US 20190031347A1 · Duan · 2019 [cited by examiner]
US 20190344902A1 · Cramblitt · 2019 [cited by applicant]
US 20190355150A1 · Tremblay et al. · 2019 [cited by applicant]
US 20190382126A1 · Rix et al. · 2019 [cited by applicant]
US 20200217666A1 · Zhang · 2020 [cited by applicant]
US 20200226426A1 · Jarquin Arroyo · 2020 [cited by applicant]
US 20210117661A1 · Iqbal · 2021 [cited by applicant]
US 20210304438A1 · Ye · 2021 [cited by applicant]
US 20210314551A1 · Tang · 2021 [cited by applicant]
US 20220108468A1 · Nakamura · 2022 [cited by applicant]
US 20220212811A1 · Khosla · 2022 [cited by examiner]
US 20220215571A1 · Leach · 2022 [cited by examiner]
US 20220258875A1 · Kyono · 2022 [cited by examiner]
US 20220276652A1 · Kyono et al. · 2022 [cited by applicant]
US 20220277472A1 · Birchfield et al. · 2022 [cited by applicant]
US 20220292772A1 · Wang · 2022 [cited by applicant]
US 20220306311A1 · Kyono · 2022 [cited by examiner]
US 20220413119A1 · Starr · 2022 [cited by applicant]
US 20220414911A1 · Wang · 2022 [cited by applicant]
US 20230244835A1 · Guo · 2023 [cited by applicant]
US 20230244905A1 · Zoldi · 2023 [cited by applicant]
US 20230281864A1 · Guo · 2023 [cited by applicant]
US 20230281945A1 · Cashman · 2023 [cited by applicant]
US 20240375786A1 · Hung et al. · 2024 [cited by applicant]
US 20240378744A1 · Smith et al. · 2024 [cited by applicant]
US 20240391494A1 · Rosenblum et al. · 2024 [cited by applicant]
US 20250011002A1 · Latib et al. · 2025 [cited by applicant]
US 20250022157A1 · Latib et al. · 2025 [cited by applicant]
US 20250164944A1 · Oyama · 2025 [cited by applicant]
US 20250171159A1 · Hung et al. · 2025 [cited by applicant]
US 20250173575A1 · Hung et al. · 2025 [cited by applicant]
US 20250173897A1 · Hung et al. · 2025 [cited by applicant]
US 20250173898A1 · Hung et al. · 2025 [cited by applicant]
US 20250190906A1 · Yin · 2025 [cited by applicant]
CN 110097574 · 2019 [cited by applicant]
EP 3566949A1 · 2019 [cited by examiner]
EP 4024340 · 2022 [cited by applicant]
EP 4024346 · 2022 [cited by applicant]
WO 2025003634 · 2025 [cited by applicant]
Gong et al. “Research of an Unmanned Aerial Vehicle Autonomous Aerial Refueling Docking Method Based on Binocular Vision” (Year: 2023). [cited by examiner]
Extended European Search Report for EP Patent Application No. 21205493.6 dated Mar. 31, 2022. [cited by applicant]
Doebbler, et al., “Boom and Receptacle Autonomous Air Refueling Using Visual Snake Optical Sensor”, Journal of Guidance and Control and Dynamics, Nov. 1, 2007, pp. 1753-1769, vol. 30, No. 6. [cited by applicant]
Anderson, et al., “Augmenting Flight Imagery from Aerial Refueling”, Oct. 21, 2019, Computer Vision—ECCV 2020 : 16th European Conference, Glasgow, UK, Aug. 23-28, 2020, pp. 154-165, Proceedings; [Lecture Notes in Comput… [cited by applicant]
Soujanya, et al. “Addressing corner detection issues for machine vision based UAV aerial refueling” Machine Vision and Applications, Springer, Jan. 10, 2007, pp. 261-276, vol. 18, No. 5, Berlin, DE. [cited by applicant]
Duan, et al., “Visual Measurement in Simulation Environment for Vision-Based UAV Autonomous Aerial Refueling”, IEEE Transactions on Instrumentation and Measurement, IEEE, USA, Sep. 1, 2015, pp. 2468-2480, vol. 64, No. 9… [cited by applicant]
Cui, et al., “Visual Servoing of a Flexible Aerial Refueling Boom With an Eye-in-Hand Camera”, IEEE Transactions on Systems, Man, and Cybernetics: Systems, IEEE, Jan. 8, 2020, pp. 6282-6292, vol. 51, No. 10, Piscataway,… [cited by applicant]
Lakshminarayanan, et al. “Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles”, 31st Conference on Neural Information Processing Systems (NIPS 2017), 2017, pp. 1-15, Long Beach, CA, USA. [cited by applicant]
Shen, et al., “Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation”, Computer Vision Foundation, 2021, pp. 707-716. [cited by applicant]
Peng, et al., “PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation”, Computer Vision Foundation, pp. 4561-4570. [cited by applicant]
Brachmann, et al., “Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image”, Computer Vision Foundation, pp. 3364-3372. [cited by applicant]
Rasmussen, C.E., “Gaussian Processes in Machine Learning”, Max Planck Institute for Biological Cybernetics, pp. 63-71, Tubingen, Germany. [cited by applicant]
Romano, et al., “Conformalized Quantile Regression”, 33rd Conference on Neural Information Processing Systems, 2019, pp. 1-11, Vancouver, Canada. [cited by applicant]
Ratzlaff, et al. “Generative Particle Variational Inference via Estimation of Functional Gradients”, Proceedings of the 38 th International Conference on Machine, 2021, pp. 1-22,. [cited by applicant]
Tobin et al., “Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World”, https://arxiv.org/pdf/1703.06907.pdf, accessed Dec. 5, 2023, pp. 1-8. [cited by applicant]
Mehta, et al. “Active Domain Randomization”, https://arxiv.org/pdf/1904.04762.pdf, accessed Dec. 5, 2023, pp. 1-15. [cited by applicant]
Akkaya. et al., “Solving Rubik's Cube With a Robot Hand”, https://arxiv.org/pdf/1910.07113.pdf, accessed Dec. 5, 2023, pp. 1-51. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24200751.6 dated Mar. 7, 2025. [cited by applicant]
Dementhon, et al., Model-Based Object Pose in 25 Lines of Code, pp. 1-9. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24196940.1 dated Mar. 7, 2025. [cited by applicant]
Wang et al., Revisiting Monocular Satellite Pose Estimation With Transformer, IEEE Transactions on Aerospace and Electronic Systems, Oct. 2022, pp. 4279-4294, vol. 58, No. 5. [cited by applicant]
Chen et al., Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement, Computer Vision Foundation, 2019, pp. 1-9. [cited by applicant]
Quang et al., Monocular Vision and Machine Learning for Pose Estimation, 2023, pp. 128-136. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24196935.1 dated Feb. 6, 2025. [cited by applicant]
Shi et al., Fast Uncertainty Quantification for Deep Object Pose Estimation, IEEE International Conference on Robotics and Automation, May 2021, pp. 5200-5207. [cited by applicant]
Vaghi et al., A Comparison of Uncertainty Estimation Approaches for DNN-based Camera Localization, Nov. 2022, pp. 1-7. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24165111.6 dated Jul. 10, 2024. [cited by applicant]
Lynch, J. C., Monocular Pose Estimation for Automated Aerial Refueling via Perspective-n-PointPerspective-n-Point, AFIT Scholar, Mar. 2022, pp. 1-76, accessed from https://scholar.afit.edu/cgi/viewcontent.cgi?article=79… [cited by applicant]
Extended European Search Report for EP Patent Application No. 24192391.1 dated Jan. 24, 2025, pp. 1-13. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24192395.2 dated Jan. 24, 2025, pp. 1-12. [cited by applicant]
Li et al., Deep Supervision with Intermediate Concepts, IEEE Transactions on Pattern Analysis and Machine Intelligence, Aug. 2019, pp. 1828-1843, vol. 41, No. 8. [cited by applicant]
Reddy et al,. Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks, 2019, IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7318-7327, IEEE Computer Society. [cited by applicant]
Park et al., Robust multi-task learning and online refinement for spacecraft pose estimation across domain gap, 2023, pp. 1-15, Advances in Space Research. [cited by applicant]
Gong et al., Research of an Unmanned Aerial Vehicle Autonomous Aerial Refueling Docking Method Based on Binocular Vision, 2023, pp. 1-21, 7, 433. [cited by applicant]
Morreale et al., Neural Semantic Surface Maps, Sep. 9, 2023, pp. 1-15,. [cited by applicant]
Reed, Benjamin B., The Restore-L Servicing Mission, Mar. 29, 2016, pp. 1-32, retrieved from URL:https://www.nasa.gov/wp-content/uploads/2015/03/reed_restorel_tagged.pdf Jan. 14, 2025. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24171550.7 dated Oct. 16, 2024, pp. 1-13. [cited by applicant]
Gupta, et al., “CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation”, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), IEEE, Oct. 27, 2019, pp. 2758-2766. [cited by applicant]
Klein, et al., “Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models”, ICASSP 2022—2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), IEEE, May 23, 202… [cited by applicant]
Shi, et al., “Fast Uncertainty Quantification for Deep Object Pose Estimation”, Arvix.org, Cornell University Library, Nov. 16, 2020, pp. 1-8. [cited by applicant]
Teng Chin-Hung, “Enhanced Outlier Removal for Extended Kalman Filter based Visual Inertial Odometry”, 2018 IEEE International Conference on Applied System Innovation (ICASI), IEEE, Apr. 13, 2018, pp. 74-77. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24182647.8 dated Oct. 24, 2024, pp. 1-7. [cited by applicant]
Extended European Search Report for EP Patent Application No. 24183945.5 dated Nov. 20, 2024, pp. 1-8. [cited by applicant]
Lee, et al., “Long-Range Pose Estimation for Aerial Refueling Approaches Using Deep Neural Networks”, Journal of Aerospace Information Systems, vol. 17, No. 11, Nov. 1, 2020, pp. 634-646. [cited by applicant]
Thomas, et al., “Advances in air to air refuelling”, Progress in Aerospace Sciences, vol. 71, Jul. 28, 2014, pp. 14-35. [cited by applicant]
Zhao, et al., “Estimating 6D Pose From Localizing Designated Surface Keypoints”, https://arxiv.org/pdf/1812.01387.pdf, accessed Dec. 5, 2023, pp. 1-9. [cited by applicant]
Xiao et al., “Simple Baselines for Human Pose Estimation and Tracking”, https://arxiv.org/pdf/1804.06208.pdf, accessed Dec. 5, 2023, pp. 1-9. [cited by applicant]
Suwajanakorn, et al., “Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning”, https://keypointnet.github.io/keypointnet_neurips.pdf, accessed Dec. 5, 2023, pp. 1-12. [cited by applicant]
Lee, et al., “Camera-to-Robot Pose Estimation from a Single Image”, 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, pp. 9426-9432, Paris, France. [cited by applicant]
Bashir, et al., “Small Object Detection in Remote Sensing Images with Residual Feature Aggregation-Based Super-Resolution and Object Detector Network”, Remote Sens., 2021, 13, 1854, pp. 1-21. [cited by applicant]
Unel, et al., “The Power of Tiling for Small Object Detection”, Computer Vision Foundation, pp. 1-10. [cited by applicant]
Lee, et al., “Online Extrinsic Camera Calibration for Temporally Consistent IPM Using Lane Boundary Observations with a Lane Width Prior”, https://arxiv.org/pdf/2008.03722.pdf, accessed Dec. 5, 2023, pp. 1-6. [cited by applicant]
Zhang, et al., “A Flexible Online Camera Calibration Using Line Segments”, Journal of Sensors, 2016, vol. 2016, Article ID 2802343, pp. 1-17, Hindawi Publishing Corporation. [cited by applicant]
Liu et al., Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness, 34th Conference on Neural Information Processing Systems, 2020, pp. 1-15, Vancouver, CA. [cited by applicant]
Guo et al., On Calibration of Modern Neural Networks, Proceedings of the 34th International Conference on Machine Learning, Aug. 3, 2017, pp. 1-14, Sydney, Australia. [cited by applicant]
Pavlakos, et al., 6-DoF Object Pose from Semantic Keypoints, 2017 IEEE Internation Conference on Robotics and Automation, pp. 1-8. [cited by applicant]
Parsons et al., Analysis of Simulated Imagery for Real-Time Vision-Based Automate Aerial Refueling, Journal of Aerospace Information Systems, Mar. 2019, pp. 77-93, vol. 16, No. 3. [cited by applicant]
Newell et al., Stacked Hourglass Networks for Human Pose Estimation, Jul. 2016, pp. 1-17, article obtain from https://arxiv.org/pdf/1603.06937 Sep. 16, 2025. [cited by applicant]
Fu, et al. “The 60 pose estimation of the aircraft using geometric property.” IEEE Transactions on Circuits and Systems for Video Technology, Jul. 2023, pp. 3358-3368, vol. 33, No. 7. [cited by applicant]
Hashemi, M., “Enlarging smaller images before inputting into convolutional neural network: zero-padding vs. interpolation.” Journal of Big Data, 2019, pp. 1-13. [cited by applicant]
Saponara, et al. Impact o Image Resizing on Deep Learning Detectors for Training Time and Model Performance, Department of Information Engineering, University of Pisa, Italy, 2022, pp. 10-17. [cited by applicant]
EP Office Action for EP Patent Application No. 24182647.8 dated Mar. 17, 2026. [cited by applicant]
Hao et al., Scale-unambiguous relative pose estimation of space uncooperative targets based on the fusion of three-dimensional time-of-flight camera and monocular camera, Optical Engineering, May 2015, pp. 1-12, vol. 54… [cited by applicant]
Oksuz et al., “Imbalance Problems in Object Detection: A Review,” Mar. 11, 2020, accessed https://arxiv.org/abs/1909.00169 on Jul. 14, 2026. [cited by applicant]
Dao et al., “Imbalance Problems in Object Detection: A Review,” Mar. 11, 2020, accessed https://arxiv.org/pdf/1803.06084 on Jul. 14, 2026. [cited by applicant]