Using machine learning to recognize variant objects

US12128567B2 · kind B2 · utility

Assignee

• AMP Robotics Corporation · US

Inventors

• Matanya B. Horowitz · Golden, US
• Joseph M. Castagneri · Denver, US
• Joshua M. Browning · Edgewater, US
• Carson C. Potter · Denver, US
• Paul J. Dawes · Redwood City, US

Key dates

• Filing date: Dec 22, 2021
• Grant date: Oct 29, 2024
• Expiry date: Jul 24, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G05B2219/50162
• WIPO field: Handling
• WIPO sector: Mechanical engineering

Abstract

Using machine learning to recognize variant objects is disclosed, including: identifying an object as a variant of an object type by inputting sensed data associated with the object into a modified machine learning model corresponding to the variant of the object type, wherein the modified machine learning model corresponding to the variant of the object type is generated using a machine learning model corresponding to the object type; and generating a control signal to provide to a sorting device that is configured to perform a sorting operation on the object, wherein the sorting operation on the object is determined based at least in part on the variant of the object type associated with the object.