US 12,384,027 B2
Detecting slippage from robotic grasp
Harry Zhe Su, Union City, CA (US); Zhouwen Sun, Redwood City, CA (US); and Samir Menon, Atherton, CA (US)
Assigned to Dexterity, Inc., Redwood City, CA (US)
Filed by Dexterity, Inc., Redwood City, CA (US)
Filed on Aug. 10, 2023, as Appl. No. 18/232,697.
Application 18/232,697 is a continuation of application No. 17/029,418, filed on Sep. 23, 2020, granted, now 11,772,262.
Claims priority of provisional application 62/926,162, filed on Oct. 25, 2019.
Prior Publication US 2024/0033906 A1, Feb. 1, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. B25J 9/16 (2006.01); B25J 13/08 (2006.01)
CPC B25J 9/1612 (2013.01) [B25J 9/163 (2013.01); B25J 9/1633 (2013.01); B25J 13/083 (2013.01); B25J 13/084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A robotic system, comprising:
a tactile sensing unit that includes a plurality of sensors, each of the plurality of sensors configured to provide a corresponding output that reflects a sensed value associated with engagement of a robotic arm end effector with an item, wherein the tactile sensing unit includes a plurality of layers, wherein the tactile sensing unit is located on a digit of the robotic arm end effector, wherein a top layer of the plurality of layers is associated with a first modality indicative of the engagement of the robotic arm end effector with the item and an intermediate layer of the plurality of layers is associated with a second modality indicative of the engagement of the robotic arm end effector with the item, wherein the first modality indicative of the engagement of the robotic arm end effector with the item is different than the second modality indicative of the engagement of the robotic arm end effector with the item; and
a processor coupled to the plurality of sensors and configured to:
use the respective outputs of the plurality of sensors to determine one or more inputs to a multi-modal model configured to provide, based at least in part on the one or more inputs, an output associated with slippage of the item within or from a grasp of the robotic arm end effector;
make based at least in part on an output of the multi-modal model a determination associated with slippage of the item within or from the grasp of the robotic arm end effector; and
take a responsive action based at least in part on the determination associated with slippage of the item within or from the grasp of the robotic arm end effector.