Systems and methods of sensor data fusion
AssigneeDigital Global Systems, Inc.
InventorArmando Montalvo
Life of this patent
Estimating the term…
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.
Claims20
A system for sensor data fusion for sensor management and utilization, comprising:
- at least one computer processor including a memory;
- at least one fusion engine, at least one inference engine, and at least one validation engine;
- at least one first sensor of a first sensor type, operable to measure a first parameter of a machine;
- and
- at least one second sensor of a second sensor type, operable to measure a second parameter of the machine;
- wherein the at least one computer processor is operable to analyze data relating to the first parameter and the second parameter;
- wherein the at least one fusion engine is operable to fuse the first parameter and the second parameter in real time, thereby creating fused data, the at least one inference engine is operable to determine at least one inference from the first parameter and the second parameter in real time, and the at least one validation engine is operable to validate the first parameter and the second parameter in real time;
- wherein the at least one inference engine determines the at least one inference by using artificial intelligence;
- wherein the at least one validation engine is operable to create a statistical comparison between the at least one inference and at least one new inference and determine if the statistical comparison exceeds a predefined threshold to automatically validate the at least one inference in real time;
- wherein the statistical comparison includes calculating a conditional entropy of data from the first parameter and the second parameter;
- wherein the at least one computer processor is operable to instruct modification of the machine based on the automatically validated at least one inference;
- and
- wherein the modification of the machine includes adjusting an orientation of a satellite.
A method for sensor data fusion for sensor management and utilization, comprising:
- providing at least one computer processor including a memory;
- providing at least one fusion engine, at least one inference engine, and at least one validation engine;
- at least one first sensor, being of a first sensor type, measuring a first parameter of a machine;
- at least one second sensor, being of a second sensor type, measuring a second parameter of the machine;
- analyzing by the at least one computer processor the first parameter and the second parameter;
- fusing the first parameter and the second parameter via the at least one fusion engine in real time, thereby creating fused data, determining at least one inference from the first parameter and the second parameter via the at least one inference engine in real time, and validating the first parameter and the second parameter via the at least one validation engine in real time;
- determining via the at least one inference engine the at least one inference by using artificial intelligence;
- comparing via the at least one validation engine the at least one inference and at least one new inference via a statistical comparison, thereby creating a validated at least one inference;
- wherein the new inference is generated in a sensor environment different from a sensor environment of the at least one inference;
- wherein the statistical comparison includes calculating a conditional entropy of data from the first parameter and the second parameter;
- instructing via the at least one computer processor modification of the machine based on the validated at least one inference;
- and
- wherein the modification of the machine includes adjusting an orientation of a satellite.
A system for sensor data fusion for sensor management and utilization, comprising:
- at least one computer processor including a memory;
- at least one fusion engine, at least one inference engine, and at least one validation engine;
- at least one first sensor, being of a first sensor type, operable to measure a first parameter of a machine;
- and
- at least one second sensor, being of a second sensor type, operable to measure a second parameter of the machine;
- wherein the at least one computer processor is operable to analyze the first parameter and the second parameter;
- wherein the at least one fusion engine is operable to fuse the first parameter and the second parameter in real time, thereby creating fused data, the at least one inference engine is operable to determine at least one inference from the first parameter and the second parameter in real time, and the at least one validation engine is operable to validate the first parameter and the second parameter in real time;
- wherein the at least one inference engine determines the at least one inference by using artificial intelligence;
- wherein the at least one validation engine is operable to create a statistical comparison between the at least one inference and at least one new inference, thereby creating a validated at least one inference;
- wherein the at least one new inference is generated in a sensor environment different from a sensor environment of the at least one inference;
- wherein the statistical comparison includes calculating a conditional entropy of data from the first parameter and the second parameter;
- wherein the at least one computer processor is operable to instruct modification of the machine based on the validated at least one inference;
- and
- wherein the modification of the machine includes adjusting an orientation of a satellite.
Dependencies are inferred from the claim text.