Rare pose data generation
AssigneeWaymo LLC
InventorsXiaohan Jin, Junhua Mao, Ruizhongtai Qi, Congcong Li, Huayi Zeng
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating rare pose data. One of the methods includes obtaining a three-dimensional model of a dynamic object, wherein the dynamic object has multiple movable elements that define a plurality of poses of the dynamic object. A plurality of template poses of the dynamic object are used to generate additional poses for the dynamic object including varying angles of one or more key joints of the dynamic object according to the three-dimensional model. Point cloud data is generated for the additional poses generated for the dynamic object.
Claims20
A computer-implemented method comprising:
- obtaining a three-dimensional model of a dynamic object, wherein the dynamic object has multiple movable elements that define a plurality of poses of the dynamic object;
- obtaining a plurality of template poses of the dynamic object;
- generating additional poses for the dynamic object including varying angles of one or more key joints of the dynamic object based on the three-dimensional model;
- and
- generating point cloud data for the additional poses generated for the dynamic object,
- wherein the point cloud data generated for the additional poses is used to train a perception model of an autonomous vehicle to recognize dynamic objects.
A system comprising:
- one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
- obtaining a three-dimensional model of a dynamic object, wherein the dynamic object has multiple movable elements that define a plurality of poses of the dynamic object;
- obtaining a plurality of template poses of the dynamic object;
- generating additional poses for the dynamic object including varying angles of one or more key joints of the dynamic object based on the three-dimensional model;
- and
- generating point cloud data for the additional poses generated for the dynamic object,
- wherein the system is configured to use the point cloud data generated for the additional poses to train a perception model of an autonomous vehicle to recognize dynamic objects.
One or more non-transitory computer storage media encoded with computer program instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:
- obtaining a three-dimensional model of a dynamic object, wherein the dynamic object has multiple movable elements that define a plurality of poses of the dynamic object;
- obtaining a plurality of template poses of the dynamic object;
- generating additional poses for the dynamic object including varying angles of one or more key joints of the dynamic object based on the three-dimensional model;
- and
- generating point cloud data for the additional poses generated for the dynamic object,
- wherein the one or more computers are configured to use the point cloud data generated for the additional poses to train a perception model of an autonomous vehicle to recognize dynamic objects.
Dependencies are inferred from the claim text.