# US 2021/0239498 A1 · Sensor fusion as a service > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0239498 A1 - Document ID: US20210239498A1 - Status: Published application - Kind: A1 - Application number: 16/991,680 - Filed: 2020-08-12 - Published: 2021-08-05 - Earliest claimed: 2020-01-23 - Assignees: Cisco Technology, Inc. - Applicants: Cisco Technology, Inc. - Inventors: Marcelo Yannuzzi Sanchez; Carlos M. Pignataro; Hervé Muyal; Simon Dyke - Web page: https://patentgrep.com/patent/US20210239498A1 ## CPC - G01D 21/02: Measuring two or more variables by means not covered by a single other subclass - G06F 9/547: {Remote procedure calls [RPC]; Web services} - G01D: MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Methods and systems for sensor fusion as a service include receiving a sensor fusion intent descriptive of desired data from a specified environment; determining candidate sensors present in the specified environment that may be used to obtain at least a portion of the desired data; and transforming the sensor fusion intent into a sensor fusion manifest by selecting a plurality of the candidate sensors to obtain respective output data, and by defining at least one action to fuse the respective output data into the desired data, wherein the sensor fusion manifest includes an identification of the selected candidate sensors and the at least one action to fuse the respective output data from the selected candidate sensors into the desired data. ## Claims ### Claim 1 A method comprising: receiving a sensor fusion intent descriptive of desired data from a specified environment; determining candidate sensors present in the specified environment that may be used to obtain at least a portion of the desired data; and transforming the sensor fusion intent into a sensor fusion manifest by selecting a plurality of the candidate sensors to obtain respective output data, and by defining at least one action to fuse the respective output data into the desired data, wherein the sensor fusion manifest includes an identification of the selected candidate sensors and the at least one action to fuse the respective output data from the selected candidate sensors into the desired data. ### Claim 2 (depends on 1) The method of claim 1, wherein the determining the candidate sensors present in the specified environment includes identifying candidate sensors from a registry of smart objects that identifies the candidate sensors and their associated functions, the smart objects being digital replicas of the candidate sensors in the specified environment. ### Claim 3 (depends on 1) The method of claim 1, wherein sensor fusion algorithms available for fusing data are cataloged in a sensor fusion tool store storing a plurality of algorithms available to fuse data received from a combination of sensors, wherein the defining at least one action to fuse the respective output data into the desired data comprises: determining at least one algorithm to fuse the respective output data into the desired data from the sensor fusion tool store. ### Claim 4 (depends on 1) The method of claim 1, wherein the sensor fusion intent includes a spatial requirement, a temporal requirement, a spatiotemporal requirement, or a domain type. ### Claim 5 (depends on 2) The method of claim 2, comprising: sending the sensor fusion manifest to be carried out on a remote computing system. ### Claim 6 (depends on 2) The method of claim 2, comprising: after receiving the sensor fusion intent, analyzing the sensor fusion intent using semantic mapping, ontologies, or natural language processing to extract information used to identify the candidate sensors from the registry of smart objects. ### Claim 7 (depends on 1) The method of claim 1, comprising: after receiving the sensor fusion intent, analyzing the sensor fusion intent using semantic mapping, ontologies, or natural language processing to extract information used to identify at least one algorithm from a sensor fusion tool store storing a plurality of algorithms available to fuse data received from a combination of sensors. ### Claim 8 (depends on 1) The method of claim 1, wherein the manifest further includes spatial, temporal, or spatial temporal relationships between where and when the output data is to be retrieved and fused. ### Claim 9 (depends on 2) The method of claim 2, further comprising performing a closed loop adjustment of the sensors associated with the smart objects based on analyzing the sensor fusion manifest under deployment. ### Claim 10 (depends on 5) The method of claim 5, wherein the smart objects comprise an application programmable interface (API) for receiving requests for data from the remote computing system. ### Claim 11 A sensor fusion system comprising: a smart object registry storing a definition of a plurality of smart objects, the smart objects being digital replicas of a plurality of sensors in a particular environment, the definition of the smart objects including data available from a sensor and/or a method inherent to the sensor; a sensor fusion tool store storing a plurality of algorithms available to fuse data received from a combination of sensors; and at least one processor configured to: receive a sensor fusion intent descriptive of desired data from a specified environment; determine candidate sensors present in the specified environment that may be used to obtain at least a portion of the desired data; and transform the sensor fusion intent into a sensor fusion manifest by selecting a plurality of the candidate sensors to obtain respective output data, and by defining at least one action to fuse the respective output data into the desired data, wherein the sensor fusion manifest includes an identification of the selected candidate sensors and the at least one action to fuse the respective output data from the selected candidate sensors into the desired data. ### Claim 12 (depends on 11) The system of claim 11, wherein the at least one processor configured to determine the candidate sensors present in the specified environment is configured to identify candidate sensors from the smart object registry. ### Claim 13 (depends on 11) The system of claim 11, wherein the at least one processor configured to define the at least one action to fuse the respective output data into the desired data is configured to: determine at least one algorithm to fuse the respective output data into the desired data from the sensor fusion tool store. ### Claim 14 (depends on 11) The system of claim 11, wherein the sensor fusion intent includes a spatial requirement, a temporal requirement, a spatiotemporal requirement, or a domain type. ### Claim 15 (depends on 12) The system of claim 12, wherein the at least one processor is further configured to: send the sensor fusion manifest to be carried out on a remote computing system. ### Claim 16 (depends on 12) The system of claim 12, wherein the at least one processor is further configured to: after receiving the sensor fusion intent, analyze the sensor fusion intent using semantic mapping, ontologies, or natural language processing to extract information used to identify the candidate sensors from the smart object registry. ### Claim 17 (depends on 11) The system of claim 11, wherein the at least one processor is further configured to: after receiving the sensor fusion intent, analyze the sensor fusion intent using semantic mapping, ontologies, or natural language processing to extract information used to identify at least one algorithm from the sensor fusion tool store. ### Claim 18 (depends on 11) The system of claim 11, wherein the manifest further includes spatial, temporal, or spatial temporal relationships between where and when the output data is to be retrieved and fused. ### Claim 19 (depends on 12) The system of claim 12, wherein the at least one processor is further configured to perform a closed loop adjustment of the sensors associated with the smart objects based on analyzing the sensor fusion manifest under deployment. ### Claim 20 (depends on 15) The system of claim 15, wherein the smart objects comprise an application programmable interface (API) for receiving requests for data from the remote computing system.