US 12,076,869 B2
Effective calculation method of the minimum distance to dynamic objects
Chiara Landi, Reggio Emilia (IT); Hsien-Chung Lin, Fremont, CA (US); and Tetsuaki Kato, Fremont, CA (US)
Assigned to FANUC CORPORATION, Yamanashi (JP)
Filed by FANUC CORPORATION, Yamanashi (JP)
Filed on Nov. 29, 2021, as Appl. No. 17/456,771.
Prior Publication US 2023/0166406 A1, Jun. 1, 2023
Int. Cl. B25J 9/16 (2006.01); B25J 13/08 (2006.01); G06T 7/00 (2017.01); G06T 7/13 (2017.01); G06T 7/50 (2017.01)
CPC B25J 9/1697 (2013.01) [B25J 9/1607 (2013.01); B25J 9/1666 (2013.01); B25J 13/089 (2013.01); G06T 7/0004 (2013.01); G06T 7/13 (2017.01); G06T 7/50 (2017.01); G06T 2207/20024 (2013.01); G06T 2207/20192 (2013.01); G06T 2207/20224 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for calculating a minimum distance from a robot to obstacles in a workspace of the robot, said method comprising:
providing an image of the workspace from a three-dimensional camera;
performing edge filtering on the image, using a computer having a processor and memory, resulting in an edge image having only pixels which define edges of items in the workspace;
subtracting the robot and background items from the edge image, resulting in a dynamic object edge pixel image;
assigning a depth value to each pixel in the dynamic object edge pixel image to create a final image, where the depth value is taken from depth data in the image provided by the camera;
determining whether a number of pixels in the final image is greater than a predefined threshold;
computing a distance from each pixel in the final image to each of a plurality of control points on the robot when the number of pixels is greater than the threshold;
determining a minimum robot-obstacle distance from the computed distances; and
determining that no obstacles exist in the workspace when the number of pixels in the final image is less than or equal to the threshold.