IP Library Granted Patent US 12,339,630
Granted Patent B2
US 12,339,630 · App. 19/016,241 · Granted Jun 24, 2025

Systems and methods of sensor data fusion

Inventor: Armando Montalvo (Winter Garden, FL)
Assignee: Digital Global Systems, Inc.
G05B13/0205B25J9/163B25J9/1694B60R19/483B60W10/18B60W30/085B60W30/09B60W60/00B60W60/0018B60W60/00186G01C3/00G01C21/1652G01C21/3804G01C21/3811G01C21/3848G01C22/00G01S5/14G01S7/4808G01S13/08G01S13/103G01S15/08G01S17/08G06F16/24G06F16/245G06F16/2455G06F16/903G06F16/90335G06F16/9035G06F18/217G06F18/2431G06F18/25G06F18/251G06N5/022G06N5/04G06N5/046G06N20/00G06T7/521G06V10/764G06V20/56G08G1/0133G08G1/04G08G1/042H04L67/12H04W4/38B60W2050/0052B60W2420/00B60W2420/40B60W2420/50B60W2510/069B60W2510/18B60W2520/04B60W2540/12B60W2556/35B60W2710/18G01S2013/93185G05D2101/15G05D2111/50G05D2111/67G06F17/18G06F18/213G06F18/256G06T2207/20024G06V10/80G08B29/188
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 12,339,630
App. No.
19/016,241
Granted
Jun 24, 2025
Kind
B2
Abstract

Systems and methods of sensor data fusion including sensor data capture, curation, linking, fusion, inference, and validation. The systems and methods described herein reduce computational demand and processing time by curating data and calculating conditional entropy. The system is operable to fuse data from a plurality of sensor types. A computer processor optionally stores fused sensor data that the system validates above a mathematical threshold.

Claims (59)

1. A system for sensor data fusion for sensor management and utilization in robotics, comprising:

at least one computer processor including a memory;

at least one curation engine, at least one link engine, at least one fusion engine, at least one inference engine, and at least one validation engine;

at least one first position sensor operable to capture a first position measurement of a robotic component; and

at least one second position sensor operable to capture a second position measurement of the robotic component;

wherein the at least one computer processor is operable to analyze the first position measurement and the second position measurement;

wherein the at least one computer processor is operable to receive at least one query;

wherein the at least one curation engine is operable to curate the first position measurement and the second position measurement, thereby creating a curated first position measurement and a curated second position measurement, the at least one link engine is operable to link the first position measurement and the second position measurement, the at least one fusion engine is operable to fuse the first position measurement and the second position measurement, the at least one inference engine is operable to determine at least one inference from the first position measurement and the second position measurement, and the at least one validation engine is operable to validate the first position measurement and the second position measurement;

wherein the at least one link engine is operable to link the curated first position measurement and the curated second position measurement based in part on at least one first position property and/or at least one first position sub-property and at least one second position property and/or at least one second position sub-property;

wherein the at least one link engine is operable to calculate a conditional entropy between the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second position sub-property based in part on the at least one query;

wherein the at least one link engine is operable to determine if the link between the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second position sub-property is a non-existent link, a weak link, or a strong link via the conditional entropy;

wherein the at least one fusion engine is operable to fuse the first position measurement and the second position measurement;

wherein the at least one fusion engine creates at least one new data set; and

wherein the at least one computer processor is operable to instruct the robotic component to move based on the at least one new data set.

2. The system of claim 1 , wherein the at least one curation engine is operable to use artificial intelligence to determine the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second position sub-property for the at least one link engine to calculate the conditional entropy.

3. The system of claim 1 , wherein the non-existent link is a conditional entropy of 1 , the weak link is a conditional entropy of between less than 1 and greater than or equal to 0.45, and the strong link is a conditional entropy of between less than 0.45 and 0.

4. The system of claim 1 , wherein the at least one query is user and/or computer generated.

5. The system of claim 1 , wherein the at least one link engine is operable to iteratively calculate the conditional entropy of the weak link until the at least one link engine calculates the non-existent link or the strong link.

6. The system of claim 1 , wherein the at least one link engine is operable to link the curated first position measurement and the curated second position measurement in real-time.

7. The system of claim 1 , wherein the system does not store the first position measurement and/or the second position measurement unless the at least one validation engine validates fused sensor data.

8. The system of claim 1 , wherein the at least one first position sensor and/or the at least one second position sensor is operable to include an accelerometer, a gyroscope, a force/torque sensor, a proximity sensor, a gear sensor, a magnetic field sensor, angle sensor, and/or a 6-axis combo inertial sensor.

9. A method for sensor data fusion for sensor management and utilization in robotics, comprising:

providing at least one computer processor including a memory;

providing at least one curation engine, at least one link engine, at least one fusion engine, at least one inference engine, and at least one validation engine;

at least one first position sensor capturing a first position measurement of a robotic component;

at least one second position sensor capturing a second position measurement of the robotic component;

analyzing by the at least one computer processor the first position measurement and the second position measurement;

receiving by the at least one computer processor at least one query;

curating by the at least one curation engine the first position measurement and the second position measurement, thereby creating a curated first position measurement and a curated second position measurement, linking by the at least one link engine the first position measurement and the second position measurement, fusing by the at least one fusion engine the first position measurement and the second position measurement, determining by the at least one inference engine at least one inference from the first position measurement and the second position measurement, and validating by the at least one validation engine the first position measurement and the second position measurement;

linking by the at least one link engine the curated first position measurement and the curated second position measurement based in part on at least one first position property and/or at least one first position sub-property and at least one second position property and/or at least one second position sub-property;

calculating by the at least one link engine a conditional entropy between the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second position sub-property based in part on the at least one query;

determining by the at least one link engine if the link between the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second position sub-property is a non-existent link, a weak link, or a strong link via the conditional entropy;

fusing by the at least one fusion engine the first position measurement and the second position measurement;

creating by the at least one fusion engine at least one new data set; and

instructing by the at least one computer processor the robotic component to move based on the at least one new data set.

10. The method of claim 9 , wherein the non-existent link is a conditional entropy of 1 , the weak link is a conditional entropy of between less than 1 and greater than or equal to 0.45, and the strong link is a conditional entropy of between less than 0.45 and 0.

11. The method of claim 9 , further comprising categorizing via the at least one curation engine the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second sub-property for the at least one link engine to calculate the conditional entropy based in part on historical accuracy of previous categorizations using artificial intelligence.

12. The method of claim 9 , wherein the at least one query is user and/or computer generated.

13. The method of claim 9 , further comprising iterating calculations so that the at least one link engine continuously calculates the conditional entropy of the weak link until the at least one link engine calculates the non-existent link or the strong link.

14. The method of claim 9 , further comprising dynamically adjusting via the at least one link engine the threshold for the non-existent link, the weak link, or the strong link depending in part on the at least one query.

15. A system for sensor data fusion for sensor management and utilization in robotics, comprising:

at least one computer processor including a memory;

at least one curation engine, at least one link engine, at least one fusion engine, at least one inference engine, and at least one validation engine; and

at least two sensors, each of the at least two sensors operable to measure a first position of a robotic component and a second position of the robotic component;

wherein the at least one computer processor is operable to analyze the first position and the second position;

wherein the at least one computer processor is operable to receive at least one query;

wherein the at least one curation engine is operable to curate the first position and the second position, thereby creating a curated first position and a curated second position, the at least one link engine is operable to link the first position and the second position, the at least one fusion engine is operable to fuse the first position and the second position, the at least one inference engine is operable to determine at least one inference from the first position and the second position, and the at least one validation engine is operable to validate the first position and the second position;

wherein the at least one link engine is operable to link the curated first position and the curated second position based in part on at least one first position property and/or at least one first position sub-property and at least one second position property and/or at least one second position sub-property;

wherein the at least one first position property and/or the at least one first position sub-property is the same as the at least one second position property and/or the at least one second position sub-property;

wherein the at least one link engine is operable to calculate a conditional entropy between the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second position sub-property based in part on the at least one query;

wherein the at least one link engine is operable to determine if the link between the at least one first position property and/or the at least one first position sub-property and the at least one second position property and/or the at least one second position sub-property is a non-existent link, a weak link, or a strong link via the conditional entropy;

wherein the at least one fusion engine is operable to fuse the first position and the second position;

wherein the at least one fusion engine creates at least one new data set; and

wherein the at least one computer processor is operable to instruct the robotic component to move based on the at least one new data set.

16. The system of claim 15 , wherein the non-existent link is a conditional entropy of 1 , the weak link is a conditional entropy of between less than 1 and greater than or equal to 0.45, and the strong link is a conditional entropy of between less than 0.45 and 0.

17. The system of claim 15 , wherein the at least one link engine is operable to link the curated first position and the curated second position in real-time.

18. The system of claim 15 , wherein the at least one query is user and/or computer generated.

19. The system of claim 15 , wherein the system does not store the first position or the second position unless the at least one validation engine validates fused sensor data.

20. The system of claim 15 , wherein the at least one link engine is operable to dynamically adjust the threshold for the non-existent link, the weak link, or the strong link depending in part on the at least one query.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 13, 2025
From: MONTALVO, ARMANDO
To: DIGITAL GLOBAL SYSTEMS, INC.
Reel/Frame 070214/0056 →
Continuity (3)
Continuation 18990121 · Dec 20, 2024
Continuation 18988120 · Dec 19, 2024
Related Publication 20250148054A1 · May 8, 2025
References Cited (75)
US 9367683B2 · Kolacinski et al. · 2016 [cited by applicant]
US 10095230B1 · Hardin · 2018 [cited by applicant]
US 10748075B2 · Chowdhary et al. · 2020 [cited by applicant]
US 10766137B1 · Porter et al. · 2020 [cited by applicant]
US 11037320B1 · Ebrahimi Afrouzi et al. · 2021 [cited by applicant]
US 11586865B2 · Brahma et al. · 2023 [cited by applicant]
US 20040019575A1 · Talbot et al. · 2004 [cited by applicant]
US 20070239314A1 · Kuvich · 2007 [cited by applicant]
US 20080312756A1 · Grichnik et al. · 2008 [cited by applicant]
US 20120134280A1 · Rotvold et al. · 2012 [cited by applicant]
US 20150306770A1 · Mittal et al. · 2015 [cited by applicant]
US 20170004411A1 · Hassan et al. · 2017 [cited by applicant]
US 20170048010A1 · Chowdhery et al. · 2017 [cited by applicant]
US 20180284758A1 · Cella et al. · 2018 [cited by applicant]
US 20190206400A1 · Cui et al. · 2019 [cited by applicant]
US 20190258251A1 · Ditty et al. · 2019 [cited by applicant]
US 20190295001A1 · Fusco et al. · 2019 [cited by applicant]
US 20200026289A1 · Alvarez et al. · 2020 [cited by applicant]
US 20200303033A1 · Benz et al. · 2020 [cited by applicant]
US 20200405403A1 · Shelton, IV et al. · 2020 [cited by applicant]
US 20210150230A1 · Smolyanskiy et al. · 2021 [cited by applicant]
US 20210290311A1 · Fuerst et al. · 2021 [cited by applicant]
US 20210342656A1 · Mittal et al. · 2021 [cited by applicant]
US 20220012562A1 · Lazaro-Gredilla et al. · 2022 [cited by applicant]
US 20220075077A1 · Kato et al. · 2022 [cited by applicant]
US 20220126864A1 · Moustafa et al. · 2022 [cited by applicant]
US 20220146652A1 · Cardei et al. · 2022 [cited by applicant]
US 20220161815A1 · Van Beek · 2022 [cited by examiner]
US 20220179056A1 · Braley et al. · 2022 [cited by applicant]
US 20220324464A1 · Collin · 2022 [cited by examiner]
US 20230082656A1 · Li et al. · 2023 [cited by applicant]
US 20230110027A1 · Bajpayee et al. · 2023 [cited by applicant]
US 20230112441A1 · Tang et al. · 2023 [cited by applicant]
US 20230149101A1 · Mottram et al. · 2023 [cited by applicant]
US 20230166765A1 · Yoon et al. · 2023 [cited by applicant]
US 20230182768A1 · Oh · 2023 [cited by applicant]
US 20230256618A1 · Park et al. · 2023 [cited by applicant]
US 20230270506A1 · Goodchild et al. · 2023 [cited by applicant]
US 20230342944A1 · Sullivan et al. · 2023 [cited by applicant]
US 20230347517A1 · Ma et al. · 2023 [cited by applicant]
US 20240045426A1 · Ditty et al. · 2024 [cited by applicant]
US 20240058948A1 · Zhai et al. · 2024 [cited by applicant]
US 20240112428A1 · Levi et al. · 2024 [cited by applicant]
US 20240123619A1 · Ning · 2024 [cited by applicant]
US 20240138926A1 · Goodchild et al. · 2024 [cited by applicant]
US 20240142994A1 · Ebrahimi Afrouzi · 2024 [cited by applicant]
US 20240152734A1 · Ye · 2024 [cited by applicant]
US 20240249165A1 · Roche et al. · 2024 [cited by applicant]
US 20240289930A1 · Yang et al. · 2024 [cited by applicant]
US 20240289981A1 · Kuo et al. · 2024 [cited by applicant]
US 20240296044A1 · Day et al. · 2024 [cited by applicant]
US 20240312219A1 · Choi et al. · 2024 [cited by applicant]
US 20240317254A1 · Tran · 2024 [cited by applicant]
US 20240324838A1 · Ebrahimi Afrouzi · 2024 [cited by applicant]
US 20240331403A1 · Shen et al. · 2024 [cited by applicant]
US 20240378412A1 · Schrader · 2024 [cited by applicant]
US 20240382216A1 · Hage et al. · 2024 [cited by applicant]
US 20240408495A1 · Hibi et al. · 2024 [cited by applicant]
US 20250026371A1 · Andert et al. · 2025 [cited by applicant]
CN 110598299A · 2019 [cited by applicant]
CN 110909762A · 2020 [cited by applicant]
CN 115561795A · 2023 [cited by applicant]
CN 116522279A · 2023 [cited by applicant]
CN 118427205A · 2024 [cited by applicant]
WO 2024186551A1 · 2024 [cited by applicant]
WO 2024228863A1 · 2024 [cited by applicant]
Yeong, D. J., Velasco-Hernandez, G., Barry, J., & Walsh, J. (2021). Sensor and sensor fusion technology in autonomous vehicles: A review. Sensors, 21(6), 2140. (Year: 2021). [cited by applicant]
Chen et al., “Track correlation uncertainty evaluation for Multi-sensor Data Fusion System and its application” 2021 IEEE (Year: 2021). [cited by applicant]
Peli et al., “Feature Level Sensor Fusion” Part of the SPIE Conference on Sensor Fusion: Architectures. Algorithms, and Applications III. Orlando, Florida, Apr. 1999 (Year: 1999). [cited by applicant]
Ebel, Patrick, and et al. “SEN12MS-CR-TS: A remote-sensing data set for multi modal multitemporal cloud removal.” IEEE Transactions on Geoscience and Remote Sensing 60 (2022): 1-14 (Year: 2022). [cited by applicant]
Wei Z, and et al. MmWave Radar and Vision Fusion for Object Detection in Autonomous Driving: A Review. Sensors (Basel). Mar. 25, 2022;22(7):2542. doi: 10.3390/s22072542. PMID: 35408157; PMCID: PMC9003130 (Year: 2022). [cited by applicant]
Brush, “Measurement of microwave power—A review of techniques used for measurement of high-frequency RF power” IEEE Instrumentation & Measurement Magazine Apr. 2007 (Year: 2007). [cited by applicant]
Kleber et al., “Cooperative Cross-Correlation Algorithm to Optimize Linearity of Fused RF Sensors” IEEE Sensors Journal, vol. 20, No. 7, Apr. 1, 2020 (Year: 2020). [cited by applicant]
Lanegger et al., “To Fuse or Not to Fuse: Measuring Consistency in Multi-Sensor Fusion for Aerial Robots” Springer, Aug. 2024 (Year: 2024). [cited by applicant]
Liu et al., “A Method for Improving the Pose Accuracy of a Robot Manipulator Based on Multi-Sensor Combined Measurement and Data Fusion” Sensors 2015, 15, 7933-7952 (Year: 2015). [cited by applicant]
Cited By (2)
US 12,554,232 US 12,576,534