知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.02 seconds)

    ACTION-CONDITIONAL IMPLICIT DYNAMICS OF DEFORMABLE OBJECTS
    6.
    发明公开
    ACTION-CONDITIONAL IMPLICIT DYNAMICS OF DEFORMABLE OBJECTS 审中-公开

    公开(公告)号：US20230290057A1

    公开(公告)日：2023-09-14

    申请号：US17691723

    申请日：2022-03-10

    Applicant: NVIDIA Corporation

    Inventor： Yuke Zhu ,  Bokui Shen ,  Christopher Bongsoo Choy ,  Animashree Anandkumar

    IPC: G06T17/10 ,  G06T19/20 ,  G06N20/20

    CPC classification number: G06T17/10 ,  G06N20/20 ,  G06T19/20 ,  G06T2219/2021

    Abstract: One or more machine learning models (MLMs) may learn implicit 3D representations of geometry of an object and of dynamics of the object from performing an action on the object. Implicit neural representations may be used to reconstruct high-fidelity full geometry of the object and predict a flow-based dynamics field from one or more images, which may provide a partial view of the object. Correspondences between locations of an object may be learned based at least on distances between the locations on a surface corresponding to the object, such as geodesic distances. The distances may be incorporated into a contrastive learning loss function to train one or more MLMs to learn correspondences between locations of the object, such as a correspondence embedding field. The correspondences may be used to evaluate state changes when evaluating one or more actions that may be performed on the object.

    FINE-TUNING POLICIES TO FACILITATE CHAINING
    7.
    发明公开
    FINE-TUNING POLICIES TO FACILITATE CHAINING 审中-公开

    公开(公告)号：US20230280726A1

    公开(公告)日：2023-09-07

    申请号：US17684245

    申请日：2022-03-01

    Applicant: NVIDIA Corporation

    Inventor： Yuke Zhu ,  Anima Anandkumar ,  Youngwoon Lee

    IPC: G05B19/418

    CPC classification number: G05B19/41865 ,  G05B19/41885 ,  G05B19/41895

    Abstract: A manipulation task may include operations performed by one or more manipulation entities on one or more objects. This manipulation task may be broken down into a plurality of sequential sub-tasks (policies). These policies may be fine-tuned so that a terminal state distribution of a given policy matches an initial state distribution of another policy that immediately follows the given policy within the plurality of policies. The fine-tuned plurality of policies may then be chained together and implemented within a manipulation environment.

    Action-conditional implicit dynamics of deformable objects
    9.
    发明授权
    Action-conditional implicit dynamics of deformable objects 有权

    公开(公告)号：US12165258B2

    公开(公告)日：2024-12-10

    申请号：US17691723

    申请日：2022-03-10

    Applicant: NVIDIA Corporation

    Inventor： Yuke Zhu ,  Bokui Shen ,  Christopher Bongsoo Choy ,  Animashree Anandkumar

    IPC: G06T17/10 ,  G06N20/20 ,  G06T19/20

    Abstract: One or more machine learning models (MLMs) may learn implicit 3D representations of geometry of an object and of dynamics of the object from performing an action on the object. Implicit neural representations may be used to reconstruct high-fidelity full geometry of the object and predict a flow-based dynamics field from one or more images, which may provide a partial view of the object. Correspondences between locations of an object may be learned based at least on distances between the locations on a surface corresponding to the object, such as geodesic distances. The distances may be incorporated into a contrastive learning loss function to train one or more MLMs to learn correspondences between locations of the object, such as a correspondence embedding field. The correspondences may be used to evaluate state changes when evaluating one or more actions that may be performed on the object.

Patent Agency Ranking