US 12,454,065 B1
Generating object references from perception data in unstructured environments and related technology
Yaadhav Raaj, Beaverton, OR (US); and Juan Fernando Medrano Yax, Guatemala (GT)
Assigned to Agility Roboltics, Inc., Pittsburgh, PA (US)
Filed by Agility Robotics, Inc., Pittsburgh, PA (US)
Filed on Nov. 13, 2023, as Appl. No. 18/507,590.
Claims priority of provisional application 63/589,578, filed on Oct. 11, 2023.
Claims priority of provisional application 63/584,068, filed on Sep. 20, 2023.
Int. Cl. B25J 13/08 (2006.01); B25J 9/00 (2006.01); B25J 9/16 (2006.01); B25J 19/02 (2006.01); G06F 18/23 (2023.01); G06T 7/73 (2017.01)
CPC B25J 13/089 (2013.01) [B25J 9/0006 (2013.01); B25J 9/161 (2013.01); B25J 9/163 (2013.01); B25J 9/1697 (2013.01); B25J 19/023 (2013.01); G06F 18/23 (2023.01); G06T 7/75 (2017.01); G06T 2207/10028 (2013.01); G06T 2207/20084 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at data-processing hardware operably associated with a mobile robot, perception data corresponding to an object in an environment of the mobile robot;
generating, by the data-processing hardware and based at least partially on the perception data, a surface feature reference corresponding to a surface feature of the object;
generating, by the data-processing hardware, a preliminary object reference for the object based at least partially on an alignment between the surface feature reference and a model of the object;
generating, by the data-processing hardware and based at least partially on the perception data and the surface feature reference, a point feature reference corresponding to a point feature of the object;
generating, by the data-processing hardware, an adjusted object reference for the object based at least partially on the preliminary object reference and the point feature reference; and
controlling the mobile robot includes controlling the mobile robot based at least partially on the adjusted object reference.