US 12,350,815 B2
Robots for serving food and/or drinks
John Jungwoo Ha, Frisco, TX (US); Fangwei Li, Belmont, CA (US); Brennand Pierce, Redwood City, CA (US); and Jungju Oh, Seoul (KR)
Assigned to Bear Robotics, Inc., Redwood City, CA (US)
Filed by Bear Robotics, Inc., Redwood City, CA (US)
Filed on Apr. 19, 2023, as Appl. No. 18/136,483.
Application 18/136,483 is a continuation of application No. 16/351,409, filed on Mar. 12, 2019, granted, now 11,660,758.
Prior Publication US 2023/0249356 A1, Aug. 10, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. B25J 11/00 (2006.01); A47G 23/08 (2006.01); B25J 9/16 (2006.01); B25J 19/02 (2006.01); G05D 1/00 (2024.01); G06Q 50/12 (2012.01)
CPC B25J 11/008 (2013.01) [A47G 23/08 (2013.01); B25J 9/1697 (2013.01); G05D 1/0246 (2013.01); G05D 1/0248 (2013.01); G05D 1/0274 (2013.01); G06Q 50/12 (2013.01); B25J 19/022 (2013.01); B25J 19/023 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A robot comprising:
a bottom portion coupled above a base;
a top portion above the bottom portion;
a first camera at the bottom portion, wherein the first camera is oriented to view upward;
a second camera at the top portion, wherein the second camera is configured to view downward; and
a processing unit configured to obtain a first three-dimensional point cloud from a first object detected by the first camera and a second three-dimensional point cloud from a second object detected by the second camera and positioned at a different height from the first object, and to process the first and second three-dimensional point clouds,
wherein the processing unit is configured to remove height components from each of the points in the first three-dimensional point cloud to obtain a first two-dimensional point cloud and remove height components from each of the points in the second three-dimensional point cloud to obtain a second two-dimensional point cloud, and to combine the first and second two-dimensional point clouds to form a combined two-dimensional point cloud and generate a two-dimensional continuous obstacle boundary line based on the combined two-dimensional point cloud.