# US 12,109,593 B2 · Classification and sorting with single-board computers > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,109,593 B2 - Document ID: US12109593B2 - Status: Granted - Kind: B2 - Application number: 17/972,541 - Filed: 2022-10-24 - Published: 2023-02-16 - Granted: 2024-10-08 - Earliest claimed: 2015-07-16 - Assignees: Sortera Technologies, Inc. - Applicants: Sortera Alloys, Inc. - Inventors: Manuel Gerardo Garcia, Jr.; Nalin Kumar; Casey Lee Hughlett - Web page: https://patentgrep.com/patent/US12109593B2 ## CPC - B07B 13/003: {Separation of articles by differences in their geometrical form or by difference in their physical properties, e.g. elasticity, compressibility, hardness} - B07B 13/18: Control - B07C 5/342: according to optical properties, e.g. colour {(according to radiation transmittivity B07C5/3416)} - G06F 18/2413: based on distances to training or reference patterns - G06T 7/0006: {using a design-rule based approach} - G06V 10/46: Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features (colour feature extraction G06V10/56) - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - B07C 2501/0054: Sorting of waste or refuse - G06T 2207/30136: Metal - G06T 2207/30141: Printed circuit board [PCB] - G06V 2201/06: Recognition of objects for industrial automation - B07B: SEPARATING SOLIDS FROM SOLIDS BY SIEVING, SCREENING, SIFTING OR BY USING GAS CURRENTS; SEPARATING BY OTHER DRY METHODS APPLICABLE TO BULK MATERIAL, e.g. LOOSE ARTICLES FIT TO BE HANDLED LIKE BULK MATERIAL (wet separating processes, sorting by processes using fluent material in the same way as liquid B03; combinations of dry separating apparatus with wet separating apparatus B03B; using liquids B03B, B03D; sorting by magnetic or electrostatic separation of solid materials from solid materials or fluids, separation by high voltage electric fields B03C; centrifuges or vortex apparatus for carrying out physical processes B04; hand sorting, postal sorting, sorting by switching or other devices actuated in response to detection or measurement of some feature of articles or samples of material B07C) - B07C: POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING (specially adapted for a specific purpose covered by another class, see the relevant place, e.g. A43D33/06, B23Q7/12) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A material handling system sorts materials utilizing a vision system of multiple vision devices configured with single board computers that each implement an artificial intelligence system in order to identify or classify materials, which are then sorted into separate groups based on such an identification or classification by sorting devices that are each coupled to one of the vision devices. ## Claims ### Claim 1 A material handling system, comprising: a plurality of vision devices each configured to capture images of material pieces, wherein each of the plurality of vision devices is independently controlled by a single-board computer (“SBC”), wherein each SBC is implemented with an artificial intelligence system configured to process the captured images of the material pieces through the artificial intelligence system in order to distinguish a predetermined class of material pieces from other classes of material pieces; a conveyor system for conveying a mixture of the material pieces past the plurality of vision devices; and a plurality of sorting devices each configured to sort from the conveyor system the predetermined class of material pieces from the other classes of material pieces. ### Claim 2 (depends on 1) The material handling system as recited in claim 1, wherein each of the plurality of sorting devices is in electronic communication with one of the single-board computers. ### Claim 3 (depends on 2) The material handling system as recited in claim 2, wherein each of the plurality of vision devices includes a camera configured to capture images of a portion of the material pieces. ### Claim 4 (depends on 3) The material handling system as recited in claim 3, wherein each of the plurality of vision devices is positioned relative to the conveyor system, transversely aligned in a row perpendicular to the direction of travel of the material pieces on the conveyor system. ### Claim 5 (depends on 4) The material handling system as recited in claim 4, wherein each of the plurality of vision devices is configured to capture images of the portion of the material pieces located within a separate lane of travel of the material pieces. ### Claim 6 (depends on 5) The material handling system as recited in claim 5, wherein each of the plurality of sorting devices is configured to divert classified materials pieces within the separate lane of travel that is located downstream from its corresponding vision device. ### Claim 7 (depends on 1) The material handling system as recited in claim 1, wherein each SBC is implemented with one or more microprocessors or microcontrollers, memory, input/output (I/O) and other features required of a functional computer or microcontroller as implemented on a single circuit board. ### Claim 8 (depends on 7) The material handling system as recited in claim 7, wherein each SBC is implemented with ARM architecture. ### Claim 9 (depends on 1) The material handling system as recited in claim 1, wherein each SBC is a Raspberry Pi computer. ### Claim 10 (depends on 1) The material handling system as recited in claim 1, wherein the captured images are captured visual images. ### Claim 11 (depends on 1) The material handling system as recited in claim 1, wherein the artificial intelligence system is configured with a neural network employing one or more algorithms that compare features detected in the captured images with those stored in a knowledge base generated during a training stage. ### Claim 12 (depends on 11) The material handling system as recited in claim 11, wherein during the training stage, the one or more algorithms learn relationships between one or more specified classes of materials and their features extracted from captured image data that creates the knowledge base. ### Claim 13 (depends on 12) The material handling system as recited in claim 12, wherein during the training stage, control samples are delivered past the camera so that the one or more algorithms detect, extract, and learn what features visually represent the one or more specified classes of materials. ### Claim 14 A material handling system, comprising: a first vision device configured to capture images of material pieces, wherein the first vision device is controlled by a first single-board computer (“SBC”), wherein the first SBC is implemented with a first artificial intelligence system configured to process the captured images of the material pieces through the first artificial intelligence system in order to distinguish a first predetermined class of material pieces from other classes of material pieces; a second vision device configured to capture images of material pieces, wherein the second vision device is controlled by a second SBC, wherein the second SBC is implemented with a second artificial intelligence system configured to process the captured images of the material pieces through the second artificial intelligence system in order to distinguish a second predetermined class of material pieces from other classes of material pieces; a conveyor system for conveying a first mixture of the material pieces past the first vision device and a second mixture of the material pieces past the second vision device; a first sorting device configured to sort from the conveyor system a first group of the first predetermined class of material pieces from the other classes of material pieces, wherein the first sorting device is in electronic communication with the first SBC; and a second sorting device configured to sort from the conveyor system a second group of the second predetermined class of material pieces from the other classes of material pieces, wherein the second sorting device is in electronic communication with the second SBC. ### Claim 15 (depends on 14) The material handling system as recited in claim 14, wherein the first and second vision devices are positioned relative to the conveyor system, transversely aligned in a row perpendicular to the direction of travel of the material pieces on the conveyor system, wherein the first vision device is configured to capture images of a first portion of the material pieces located within a first lane of travel of the material pieces, and wherein the second vision device is configured to capture images of a second portion of the material pieces located within a second lane of travel of the material pieces, wherein the first and second lanes of travel are parallel to each other, wherein the first sorting device is configured to divert classified materials pieces within the first lane of travel that is located downstream from the first vision device, and wherein the second sorting device is configured to divert classified materials pieces within the second lane of travel that is located downstream from the second vision device. ### Claim 16 (depends on 14) The material handling system as recited in claim 14, wherein the first and second predetermined classes of material pieces are the same. ### Claim 17 (depends on 14) The material handling system as recited in claim 14, wherein the first and second artificial intelligence systems operate substantially similar algorithms for classifying materials. ### Claim 18 (depends on 14) The material handling system as recited in claim 14, wherein the first SBC is implemented with one or more microprocessors or microcontrollers, memory, input/output (I/O) and other features required of a functional computer or microcontroller, wherein the second SBC is implemented with one or more microprocessors or microcontrollers, memory, input/output (I/O) and other features required of a functional computer or microcontroller, wherein the first SBC is implemented on a single circuit board, and wherein the second SBC is implemented on a single circuit board. ### Claim 19 (depends on 14) The material handling system as recited in claim 14, wherein the captured images are captured visual images. ### Claim 20 (depends on 14) The material handling system as recited in claim 14, wherein the artificial intelligence system is configured with a neural network employing one or more algorithms that compare features detected in the captured images with those stored in a knowledge base generated during a training stage, wherein during the training stage, the one or more algorithms learn relationships between one or more specified classes of materials and their features extracted from captured image data that creates the knowledge base.