# US 11,991,946 B2 · Adaptively adjusting parameters of equipment operating in unpredictable terrain > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,991,946 B2 - Document ID: US11991946B2 - Status: Granted - Kind: B2 - Application number: 17/485,928 - Filed: 2021-09-27 - Published: 2023-03-30 - Granted: 2024-05-28 - Earliest claimed: 2021-09-27 - Assignees: Mineral Earth Sciences LLC - Applicants: Mineral Earth Sciences LLC - Inventors: Sergey Yaroshenko; Gabriella Levine; Elliott Grant; Daniel Ribeiro Silva; Linda Kanu; Francis Ebong - Web page: https://patentgrep.com/patent/US11991946B2 ## CPC - A01B 79/005: {Precision agriculture} - G06V 10/993: {Evaluation of the quality of the acquired pattern} - A01B 63/002: {Devices for adjusting or regulating the position of tools or wheels (preventing overstrain A01B61/00; wheels adjustable relatively to the frame for drawn implements A01B3/16; tools or tool holders adjustable relatively to the frame for drawn implements A01B63/24)} - G05D 1/0246: {using a video camera in combination with image processing means} - G06N 3/02: Neural networks - G06Q 10/063: Operations research, analysis or management - G06Q 50/02: Agriculture; Fishing; Forestry; Mining - G06V 20/188: {Vegetation} - G06N 3/09: Supervised learning - A01B: SOIL WORKING IN AGRICULTURE OR FORESTRY; PARTS, DETAILS, OR ACCESSORIES OF AGRICULTURAL MACHINES OR IMPLEMENTS, IN GENERAL (making or covering furrows or holes for sowing, planting or manuring A01C5/00; mowers convertible to soil working apparatus or capable of soil working A01D42/04; mowers combined with soil working implements A01D43/12; soil working for engineering purposes E01, E02, E21) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Implementations are disclosed for adaptively adjusting various parameters of equipment in unpredictable terrain, such as agricultural fields. In various implementations, edge computing device(s) may obtain a first image captured by vision sensor(s) transported across an agricultural field by a vehicle. The first image may depict plant(s) growing in the agricultural area. The edge computing device(s) may process the first image based on a machine learning model to generate agricultural inference(s) about the plant(s) growing in the agricultural area. The edge computing device(s) may determine a quality metric for the agricultural inference(s). While the vehicle continues to travel across the agricultural field, and based on the quality metric: the edge computing device(s) may trigger one or more hardware adjustments to one or more of the vision sensors, or one or more adjustments in an operation of the vehicle. ## Claims ### Claim 1 A method implemented using one or more edge computing devices, the method comprising: obtaining, by one or more of the edge computing devices, a first image captured by one or more vision sensors transported across an agricultural field by a vehicle, wherein the first image depicts one or more plants growing in an agricultural area; processing, by one or more of the edge computing devices, the first image to generate one or more agricultural inferences about one or more of the plants growing in the agricultural area, wherein the processing is based on a machine learning model; determining, by one or more of the edge computing devices, a quality metric for the one or more agricultural inferences using one or more of the edge computing devices, wherein the quality metric appraises or quantifies a value or reliability of one or more of the inferences; and while the vehicle continues to travel across the agricultural field, and based on the quality metric: triggering, by one or more of the edge computing devices, one or more hardware adjustments to one or more of the vision sensors, or triggering, by one or more of the edge computing devices, an adjustment in an operation of the vehicle. ### Claim 2 (depends on 1) The method of claim 1, wherein one or more of the agricultural inferences includes a visual annotation that labels a plant feature in the first image, and the quality metric is determined based on a spatial dimension of the visual annotation. ### Claim 3 (depends on 2) The method of claim 2, wherein the quality metric is determined based on a deviation of the spatial dimension from an expected spatial dimension of the plant feature. ### Claim 4 (depends on 1) The method of claim 1, wherein the one or more edge computing devices are mounted on or integral with the vehicle. ### Claim 5 (depends on 1) The method of claim 1, wherein the quality metric is determined based on a deviation of one or more of the agricultural inferences from a trajectory of agricultural inferences. ### Claim 6 (depends on 5) The method of claim 5, wherein the deviation from the trajectory is determined based on a recurrent neural network. ### Claim 7 (depends on 1) The method of claim 1, wherein the one or more vision sensors comprises a stereoscopic camera, and one or more of the hardware adjustments includes altering an interaxial distance between lenses of the stereoscopic camera. ### Claim 8 (depends on 1) The method of claim 1, wherein one or more of the hardware adjustments includes an adjustment of: an optical zoom of one or more of the vision sensors; a framerate of one or more of the vision sensors; an aperture size of one or more of the vision sensors; or an exposure speed of one or more of the vision sensors. ### Claim 9 (depends on 1) The method of claim 1, wherein the adjustment in the operation of the vehicle comprises a reduction in speed. ### Claim 10 (depends on 1) The method of claim 1, wherein the adjustment in the operation of the vehicle comprises stopping and reversing the vehicle, and wherein the method further includes: triggering one or more adjustments to a given vision sensor of the one or more vision sensors; obtaining a second image captured by the given vision sensor subsequent to the stopping and reversing of the vehicle, wherein the second image depicts one or more of the same plants growing in the agricultural area; and processing the second image based on the machine learning model to generate one or more updated agricultural inferences about one or more of the plants growing in the agricultural area. ### Claim 11 An edge computing device comprising memory and one or more processors, wherein the memory stores instructions that, in response to execution by the one or more processors, cause the one or more processors to: obtain a first image captured by one or more vision sensors transported across an agricultural field by a vehicle, wherein the first image depicts one or more plants growing in an agricultural area; process the first image to generate one or more agricultural inferences about one or more of the plants growing in the agricultural area, wherein the processing is based on a machine learning model; determine a quality metric for the one or more agricultural inferences using one or more of the edge computing devices, wherein the quality metric appraises or quantifies a value or reliability of one or more of the inferences; and while the vehicle continues to travel across the agricultural field, and based on the quality metric: trigger one or more hardware adjustments to one or more of the vision sensors, or trigger an adjustment in an operation of the vehicle. ### Claim 12 (depends on 11) The edge computing device of claim 11, wherein one or more of the agricultural inferences includes a visual annotation that labels a plant feature in the first image. ### Claim 13 (depends on 12) The edge computing device of claim 12, wherein the quality metric is determined based on a spatial dimension of the visual annotation. ### Claim 14 (depends on 13) The edge computing device of claim 13, wherein the quality metric is determined based on a deviation of the spatial dimension from an expected spatial dimension of the plant feature. ### Claim 15 (depends on 11) The edge computing device of claim 11, wherein the quality metric is determined based on a deviation of one or more of the agricultural inferences from a trajectory of agricultural inferences. ### Claim 16 (depends on 15) The edge computing device of claim 15, wherein the deviation from the trajectory is determined based on a recurrent neural network. ### Claim 17 (depends on 11) The edge computing device of claim 11, wherein the one or more vision sensors comprises a stereoscopic camera, and one or more of the hardware adjustments includes an alteration of an interaxial distance between lenses of the stereoscopic camera. ### Claim 18 (depends on 11) The edge computing device of claim 11, wherein one or more of the hardware adjustments includes an adjustment of: an optical zoom of one or more of the vision sensors; a framerate of one or more of the vision sensors; an aperture size of one or more of the vision sensors; or an exposure speed of one or more of the vision sensors. ### Claim 19 A non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a processor of an edge computing device, cause the processor to: obtain a first image captured by one or more vision sensors transported across an agricultural field by a vehicle, wherein the first image depicts one or more plants growing in an agricultural area; process the first image to generate one or more agricultural inferences about one or more of the plants growing in the agricultural area, wherein the processing is based on a machine learning model; determine a quality metric for the one or more agricultural inferences using one or more of the edge computing devices, wherein the quality metric appraises or quantifies a value or reliability of one or more of the inferences; and while the vehicle continues to travel across the agricultural field, and based on the quality metric: trigger one or more hardware adjustments to one or more of the vision sensors, or trigger an adjustment in an operation of the vehicle. ### Claim 20 (depends on 19) The non-transitory computer-readable medium of claim 19, wherein one or more of the agricultural inferences includes a visual annotation that labels a plant feature in the first image.