US 11,745,353 B2
Recovering material properties with active illumination and camera on a robot manipulator
Guy Satat, Sunnyvale, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by X Development LLC, Mountain View, CA (US)
Filed on Nov. 30, 2020, as Appl. No. 17/106,889.
Prior Publication US 2022/0168898 A1, Jun. 2, 2022
Int. Cl. G06V 10/60 (2022.01); B25J 9/16 (2006.01); B25J 19/02 (2006.01); G01N 21/359 (2014.01); G06F 18/21 (2023.01); G06F 18/24 (2023.01); H04N 23/10 (2023.01); H04N 23/56 (2023.01); H04N 23/90 (2023.01); H04N 23/695 (2023.01); G06V 10/58 (2022.01); B25J 5/00 (2006.01); G01N 21/55 (2014.01)
CPC B25J 9/1697 (2013.01) [B25J 9/163 (2013.01); B25J 9/1664 (2013.01); B25J 19/023 (2013.01); G01N 21/359 (2013.01); G06F 18/21 (2023.01); G06F 18/24 (2023.01); G06V 10/60 (2022.01); H04N 23/10 (2023.01); H04N 23/56 (2023.01); H04N 23/695 (2023.01); H04N 23/90 (2023.01); B25J 5/007 (2013.01); G01N 2021/555 (2013.01); G06V 10/58 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying a target surface in an environment of a robotic device;
controlling a moveable component of the robotic device to move along a motion path relative to the target surface, wherein the moveable component comprises a light source and a. camera;
receiving a plurality of images from the camera when the moveable component is at a plurality of poses along the motion path and when the light source is illuminating the target surface;
determining bidirectional reflectance distribution function (BRDF) image data, wherein the BRDF image data comprises the plurality of images converted to angular space with respect to the target surface; and
determining, based on the BRDF image data and by applying at least one pre-trained machine learning model, a material property of the target surface.