Global localization apparatus and method thereof
AssigneesHyundai Motor Company, Kia Corporation
InventorsChangyo LEE, Seungwon Song
Life of this patent
Estimating the term…
Abstract
In an embodiment a method includes generating, by a processor of a computing device, information for a plurality of keyframes, based on a plurality of image data obtained by using a camera mounted on a robot and robot pose data with respect to a position and orientation of the robot corresponding to each of the plurality of image data, determining, by the processor using at least one artificial intelligence module, place recognition information that identify a space with respect to each of the plurality of image data and managing, by the processor, an image gallery for supporting autonomous driving of the robot by clustering, based on the place recognition information, the plurality of keyframes into at least one group.
Claims20
A method for supporting autonomous driving of a robot, the method comprising:
- generating, by a processor of a computing device, information for a plurality of keyframes, based on a plurality of image data obtained by using a camera mounted on the robot and robot pose data with respect to a position and orientation of the robot corresponding to each of the plurality of image data;
- determining, by the processor using at least one artificial intelligence module, place recognition information that identify a space with respect to each of the plurality of image data;
- and
- managing, by the processor, an image gallery for supporting the autonomous driving of the robot by clustering, based on the place recognition information, the plurality of keyframes into at least one group.
An apparatus for supporting autonomous driving of a robot, the apparatus comprising:
- one or more non-transitory computer-readable media with instructions stored thereon;
- and
- one or more processors configured to execute the instructions by
- generating information for a plurality of keyframes, based on a plurality of image data obtained by using a camera mounted on the robot and robot pose data with respect to a position and orientation of the robot corresponding to each of the plurality of image data;
- determining, by using at least one artificial intelligence module, place recognition information that identify a space with respect to each of the plurality of image data;
- and
- managing, by clustering the plurality of keyframes into at least one group, based on the place recognition information, an image gallery for supporting the autonomous driving of the robot.
A non-transitory computer-readable medium comprising an instructions executable by a computing device, wherein the instructions cause the computing device to:
- generate information for a plurality of keyframes, based on a plurality of image data obtained by using a camera mounted on a robot and robot pose data with respect to position and orientation of the robot corresponding to each of the plurality of image data;
- determine, by using at least one artificial intelligence module, place recognition information that identify a space with respect to each of the plurality of image data;
- and
- manage, by clustering, based on the place recognition information, the plurality of keyframes into at least one group, an image gallery for supporting autonomous driving of the robot.
Dependencies are inferred from the claim text.