中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.012 seconds)

    METHOD TO INCORPORATE UNCERTAIN INPUTS INTO NEURAL NETWORKS
    1.
    发明公开
    METHOD TO INCORPORATE UNCERTAIN INPUTS INTO NEURAL NETWORKS 审中-公开

    公开(公告)号：US20230169329A1

    公开(公告)日：2023-06-01

    申请号：US17540107

    申请日：2021-12-01

    Applicant: NVIDIA Corporation

    Inventor： Fabio Tozeto Ramos ,  Rika Antonova ,  Ankur Handa ,  Dieter Fox

    IPC: G06N3/08

    CPC classification number: G06N3/08

    Abstract: Systems and methods related to incorporating uncertain inputs into a neural network are described herein. A distribution is obtained and processed by a Reproducing Kernel Hilbert Space (RKHS) module to generate an embedding that represents the distribution. The features of the embedding may correspond to a number of Random Fourier Features (RFFs). The embedding can be added to additional features to form an aggregate input for the neural network. The neural network then processes the aggregate input to generate an output based on, at least in part, the embedding of the distribution. In some embodiments, a simulation can be run to generate a distribution for a feature, where each simulator instance generates a different sample for the feature over a plurality of time steps of the simulation. In some embodiments, the output neural network can be used to control robotic systems, vehicles, or other systems.

    SIMULATION OF TASKS USING NEURAL NETWORKS
    2.
    发明申请
    SIMULATION OF TASKS USING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20200306960A1

    公开(公告)日：2020-10-01

    申请号：US16372274

    申请日：2019-04-01

    Applicant: NVIDIA Corporation

    Inventor： Ankur Handa ,  Viktor Makoviichuk ,  Miles Macklin ,  Nathan Ratliff ,  Dieter Fox ,  Yevgen Chebotar ,  Jan Issac

    IPC: B25J9/16 ,  G05B13/02 ,  G05B13/04 ,  G05D1/00

    Abstract: A machine-learning control system is trained to perform a task using a simulation. The simulation is governed by parameters that, in various embodiments, are not precisely known. In an embodiment, the parameters are specified with an initial value and expected range. After training on the simulation, the machine-learning control system attempts to perform the task in the real world. In an embodiment, the results of the attempt are compared to the expected results of the simulation, and the parameters that govern the simulation are adjusted so that the simulated result matches the real-world attempt. In an embodiment, the machine-learning control system is retrained on the updated simulation. In an embodiment, as additional real-world attempts are made, the simulation parameters are refined and the control system is retrained until the simulation is accurate and the control system is able to successfully perform the task in the real world.

    Simulation of tasks using neural networks
    3.
    发明授权
    Simulation of tasks using neural networks 有权

    公开(公告)号：US12275146B2

    公开(公告)日：2025-04-15

    申请号：US16372274

    申请日：2019-04-01

    Applicant: NVIDIA Corporation

    Inventor： Ankur Handa ,  Viktor Makoviichuk ,  Miles Macklin ,  Nathan Ratliff ,  Dieter Fox ,  Yevgen Chebotar ,  Jan Issac

    IPC: G05B13/04 ,  B25J9/16 ,  G05B13/02 ,  G05D1/00

    Abstract: A machine-learning control system is trained to perform a task using a simulation. The simulation is governed by parameters that, in various embodiments, are not precisely known. In an embodiment, the parameters are specified with an initial value and expected range. After training on the simulation, the machine-learning control system attempts to perform the task in the real world. In an embodiment, the results of the attempt are compared to the expected results of the simulation, and the parameters that govern the simulation are adjusted so that the simulated result matches the real-world attempt. In an embodiment, the machine-learning control system is retrained on the updated simulation. In an embodiment, as additional real-world attempts are made, the simulation parameters are refined and the control system is retrained until the simulation is accurate and the control system is able to successfully perform the task in the real world.

    Neural networks to generate robotic task demonstrations
    5.
    发明授权
    Neural networks to generate robotic task demonstrations 有权

    公开(公告)号：US12202147B2

    公开(公告)日：2025-01-21

    申请号：US17695756

    申请日：2022-03-15

    Applicant: NVIDIA CORPORATION

    Inventor： Ankur Handa ,  Iretiayo Akinola ,  Dieter Fox ,  Yashraj Shyam Narang

    IPC: B25J9/16

    Abstract: A technique for training a neural network, including generating a plurality of input vectors based on a first plurality of task demonstrations associated with a first robot performing a first task in a simulated environment, wherein each input vector included in the plurality of input vectors specifies a sequence of poses of an end-effector of the first robot, and training the neural network to generate a plurality of output vectors based on the plurality of input vectors. Another technique for generating a task demonstration, including generating a simulated environment that includes a robot and at least one object, causing the robot to at least partially perform a task associated with the at least one object within the simulated environment based on a first output vector generated by a trained neural network, and recording demonstration data of the robot at least partially performing the task within the simulated environment.

    IN-HAND OBJECT POSE TRACKING
    6.
    发明申请
    IN-HAND OBJECT POSE TRACKING 有权

    公开(公告)号：US20210122045A1

    公开(公告)日：2021-04-29

    申请号：US16863111

    申请日：2020-04-30

    Applicant: NVIDIA Corporation

    Inventor： Ankur Handa ,  Karl Van Wyk ,  Viktor Makoviichuk ,  Dieter Fox

    IPC: B25J9/16 ,  G05B17/02 ,  B25J13/08 ,  G06T7/73

    Abstract: Apparatuses, systems, and techniques are described that estimate the pose of an object while the object is being manipulated by a robotic appendage. In at least one embodiment, a sample-based optimization algorithm tracks in-hand object poses during manipulation via contact feedback and a GPU-accelerated robotic simulation is developed. In at least one embodiment, parallel simulations concurrently model object pose changes that may be caused by complex contact dynamics. In at least one embodiment, the optimization algorithm tunes simulation parameters during object pose tracking to further improve tracking performance. In various embodiments, real-world contact sensing may be improved by utilizing vision in-the-loop.

    FORCE ESTIMATION USING DEEP LEARNING
    9.
    发明申请
    FORCE ESTIMATION USING DEEP LEARNING 审中-公开

    公开(公告)号：US20200301510A1

    公开(公告)日：2020-09-24

    申请号：US16358485

    申请日：2019-03-19

    Applicant: NVIDIA Corporation

    Inventor： Stan Birchfield ,  Byron Boots ,  Dieter Fox ,  Ankur Handa ,  Nathan Ratliff ,  Balakumar Sundaralingam ,  Alexander Lambert

    IPC: G06F3/01 ,  G01L5/22 ,  G06N3/08 ,  G06T11/00

    Abstract: A computer system generates a tactile force model for a tactile force sensor by performing a number of calibration tasks. In various embodiments, the calibration tasks include pressing the tactile force sensor while the tactile force sensor is attached to a pressure gauge, interacting with a ball, and pushing an object along a planar surface. Data collected from these calibration tasks is used to train a neural network. The resulting tactile force model allows the computer system to convert signals received from the tactile force sensor into a force magnitude and direction with greater accuracy than conventional methods. In an embodiment, force on the tactile force sensor is inferred by interacting with an object, determining the motion of the object, and estimating the forces on the object based on a physical model of the object.

Patent Agency Ranking