US 12,403,602 B2
Robot interaction with human co-workers
David M. S. Johnson, Cambridge, MA (US); Syler Wagner, Somerville, MA (US); Steven Lines, Brookline, MA (US); Mitchell Hebert, Littleton, CO (US); and Connor Lawson, Cambridge, MA (US)
Assigned to DEXAI ROBOTICS, INC., San Diego, CA (US)
Filed by DEXAI ROBOTICS, INC., San Diego, CA (US)
Filed on Dec. 15, 2023, as Appl. No. 18/541,877.
Application 18/541,877 is a continuation of application No. 16/570,606, filed on Sep. 13, 2019, granted, now 11,872,702.
Claims priority of provisional application 62/731,398, filed on Sep. 14, 2018.
Claims priority of provisional application 62/730,934, filed on Sep. 13, 2018.
Claims priority of provisional application 62/730,918, filed on Sep. 13, 2018.
Claims priority of provisional application 62/730,933, filed on Sep. 13, 2018.
Claims priority of provisional application 62/730,947, filed on Sep. 13, 2018.
Claims priority of provisional application 62/730,703, filed on Sep. 13, 2018.
Prior Publication US 2024/0227189 A1, Jul. 11, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. B25J 9/16 (2006.01); G05B 19/4061 (2006.01)
CPC B25J 9/1666 (2013.01) [B25J 9/161 (2013.01); B25J 9/1653 (2013.01); B25J 9/1664 (2013.01); B25J 9/1674 (2013.01); B25J 9/1676 (2013.01); B25J 9/1697 (2013.01); G05B 19/4061 (2013.01); G05B 2219/39091 (2013.01); G05B 2219/40202 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for controlling a robot for object avoidance, the method comprising:
detecting a type and a location of an object based on a camera image of the object, the image having a reference frame;
predicting motion of the object based on the detected type of the object, the detected location of the object, and a physics-based dynamics model of the object, the predicting motion comprising:
selecting equations to include in the physics-based dynamics model of the object from a set of plausible models by matching the detected type of the object to an element in a library of models; and
performing a simulation using both: (i) the physics-based dynamics model of the object, including the selected equations, and (ii) a recursive Bayesian estimator configured to employ the physics-based dynamics model of the object, including the selected equations, as a system model to update the recursive Bayesian estimator, the performing the simulation providing the predicted motion of the object; and
generating a motion plan for a robot that avoids having the robot collide with the object based on:
the predicted motion of the object;
determining a transformation between the reference frame of the image and a reference frame of the robot, the determined transformation between the reference frame of the image and the reference frame of the robot enabling conversion from locations in the image to locations in relation to the robot; and
determining a time varying model of the object based on the predicted motion of the object.