	US 12,145,271 B2
	Method and system for object grasping
Li Yang Ku, Castro Valley, CA (US); Michael Stark, Mountain View, CA (US); Ahmad Humayun, Mountain View, CA (US); Nan Rong, Fremont, CA (US); and Bhaskara Mannar Marthi, Sunnyvale, CA (US)
Assigned to Intrinsic Innovation LLC, Mountain View, CA (US)
Filed by Intrinsic Innovation LLC, Mountain View, CA (US)
Filed on Dec. 29, 2022, as Appl. No. 18/091,286.
Application 18/091,286 is a continuation of application No. 17/375,424, filed on Jul. 14, 2021, granted, now 11,541,534.
Claims priority of provisional application 63/149,180, filed on Feb. 12, 2021.
Claims priority of provisional application 63/051,867, filed on Jul. 14, 2020.
Prior Publication US 2023/0321821 A1, Oct. 12, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. B25J 9/16 (2006.01); B25J 9/08 (2006.01); G05B 19/4155 (2006.01); G06N 3/08 (2023.01); G06T 7/73 (2017.01)

CPC B25J 9/1612 (2013.01) [B25J 9/08 (2013.01); B25J 9/1697 (2013.01); G05B 19/4155 (2013.01); G06N 3/08 (2013.01); G06T 7/73 (2017.01); G05B 2219/39505 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)]

20 Claims

1. A method, comprising:

determining a set of data for an object in a scene, each of the set of data comprising a respective keypoint and a corresponding object component identifier;

determining a set of candidate grasp locations for the object, using the set of data, wherein each candidate grasp location of the set of candidate grasp locations is associated with a respective occlusion score determined by a machine learning model trained on images labeled with predetermined occlusion scores for locations in the images;

determining one or more candidate grasp proposals based on the set of candidate grasp locations for grasping the object;

selecting a candidate grasp proposal from the one or more candidate grasp proposals as a final grasp proposal based on one or more criteria; and

storing the final grasp proposal in memory to be retrieved for controlling a robot to grasp the object.