US 12,128,567 B2
Using machine learning to recognize variant objects
Matanya B. Horowitz, Golden, CO (US); Joseph M. Castagneri, Denver, CO (US); Joshua M. Browning, Edgewater, CO (US); Carson C. Potter, Denver, CO (US); and Paul Dawes, Woodside, CA (US)
Assigned to AMP Robotics Corporation, Louisville, CO (US)
Filed by AMP Robotics Corporation, Louisville, CO (US)
Filed on Dec. 22, 2021, as Appl. No. 17/559,805.
Prior Publication US 2023/0191608 A1, Jun. 22, 2023
Int. Cl. B25J 9/16 (2006.01)
CPC B25J 9/1679 (2013.01) [B25J 9/163 (2013.01); B25J 9/1697 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
one or more processors configured to:
identify 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, wherein the machine learning model corresponding to the object type was modified to generate the modified machine learning model corresponding to the variant of the object type including by:
training the machine learning model corresponding to the object type using training data comprising annotated images of objects of the object type in a plurality of different conditions; and
generate 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; and
a memory coupled to the one or more processors and configured to provide the one or more processors with instructions.