The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Oct. 15, 2019

Filed:

Jun. 14, 2017
Applicant:

Zoox, Inc., Menlo Park, CA (US);

Inventors:

Bertrand Robert Douillard, Palo Alto, CA (US);

Subhasis Das, Menlo Park, CA (US);

Zeng Wang, Menlo Park, CA (US);

Dragomir Dimitrov Anguelov, San Francisco, CA (US);

Jesse Sol Levinson, Redwood City, CA (US);

Assignee:

Zoox, Inc., Foster City, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G05D 1/02 (2006.01); G01S 17/89 (2006.01); G01S 17/93 (2006.01); G06K 9/00 (2006.01); G06T 7/11 (2017.01); G01S 17/02 (2006.01); G01S 17/58 (2006.01); G01S 17/66 (2006.01); G06T 7/187 (2017.01); G01S 15/93 (2006.01); G01S 15/02 (2006.01); G01S 13/72 (2006.01); G01S 13/86 (2006.01); G01S 13/93 (2006.01);
U.S. Cl.
CPC ...
G05D 1/024 (2013.01); G01S 17/023 (2013.01); G01S 17/58 (2013.01); G01S 17/66 (2013.01); G01S 17/89 (2013.01); G01S 17/936 (2013.01); G05D 1/0212 (2013.01); G06K 9/00791 (2013.01); G06T 7/11 (2017.01); G06T 7/187 (2017.01); G01S 13/726 (2013.01); G01S 13/862 (2013.01); G01S 13/865 (2013.01); G01S 13/867 (2013.01); G01S 13/931 (2013.01); G01S 15/025 (2013.01); G01S 15/931 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/30252 (2013.01);
Abstract

Systems, methods, and apparatuses described herein are directed to performing segmentation on voxels representing three-dimensional data to identify static and dynamic objects. LIDAR data may be captured by a perception system for an autonomous vehicle and represented in a voxel space. Operations may include determining a drivable surface by parsing individual voxels to determine an orientation of a surface normal of a planar approximation of the voxelized data relative to a reference direction. Clustering techniques can be used to grow a ground plane including a plurality of locally flat voxels. Ground plane data can be set aside from the voxel space, and the remaining voxels can be clustered to determine objects. Voxel data can be analyzed over time to determine dynamic objects. Segmentation information associated with ground voxels, static object, and dynamic objects can be provided to a tracker and/or planner in conjunction with operating the autonomous vehicle.


Find Patent Forward Citations

Loading…