中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

16 records (took 0.015 seconds)

    Mitigating reality gap through modification of simulated state data of robotic simulator
    1.
    发明授权
    Mitigating reality gap through modification of simulated state data of robotic simulator 有权

    公开(公告)号：US11790042B1

    公开(公告)日：2023-10-17

    申请号：US17896519

    申请日：2022-08-26

    Applicant: X Development LLC

    Inventor： Yunfei Bai

    IPC: G06F30/20 ,  G06F18/214 ,  G06N3/08 ,  G06N20/00 ,  B25J9/16 ,  G06N3/045

    CPC classification number: G06F18/2148 ,  B25J9/1671 ,  G06N3/045 ,  G06N3/08 ,  G06N20/00

    Abstract: Mitigating the reality gap through training and utilization of at least one difference model. The difference model can be utilized to generate, for each of a plurality of instances of simulated state data generated by a robotic simulator, a corresponding instance of modified simulated state data. The difference model is trained so that a generated modified instance of simulated state data is closer to “real world data” than is a corresponding initial instance of simulated state data. Accordingly, the difference model can be utilized to mitigate the reality gap through modification of initially generated simulated state data, to make it more accurately reflect what would occur in a real environment. Moreover, the difference representation from the difference model can be used as input to the control policy to adapt the control learned from simulator to the real environment.

    Machine learning methods and apparatus for robotic manipulation and that utilize multi-task domain adaptation
    2.
    发明授权
    Machine learning methods and apparatus for robotic manipulation and that utilize multi-task domain adaptation 有权

    公开(公告)号：US10773382B2

    公开(公告)日：2020-09-15

    申请号：US15913212

    申请日：2018-03-06

    Applicant: X Development LLC

    Inventor： Yunfei Bai ,  Kuan Fang ,  Stefan Hinterstoisser ,  Mrinal Kalakrishnan

    IPC: B25J9/16

    Abstract: Implementations are directed to training a machine learning model that, once trained, is used in performance of robotic grasping and/or other manipulation task(s) by a robot. The model can be trained using simulated training examples that are based on simulated data that is based on simulated robot(s) attempting simulated manipulations of various simulated objects. At least portions of the model can also be trained based on real training examples that are based on data from real-world physical robots attempting manipulations of various objects. The simulated training examples can be utilized to train the model to predict an output that can be utilized in a particular task—and the real training examples used to adapt at least a portion of the model to the real-world domain can be tailored to a distinct task. In some implementations, domain-adversarial similarity losses are determined during training, and utilized to regularize at least portion(s) of the model.

    Determining robot inertial properties
    3.
    发明授权
    Determining robot inertial properties 有权

    公开(公告)号：US10967505B1

    公开(公告)日：2021-04-06

    申请号：US16703101

    申请日：2019-12-04

    Applicant: X Development LLC

    Inventor： Yunfei Bai

    IPC: B25J9/16

    Abstract: Methods and systems for modifying the inertial parameters used in a virtual robot model that simulates the interactions of a real-world robot with an environment to better reflect the actual inertial properties of the real-world robot. In one aspect, a method includes obtaining joint physical parameter measurements for the joints of a real-world robot, determining simulated joint physical parameter values for each of the joint physical parameter measurements, and adjusting an estimate of inertial properties of the real-world robot used by the virtual robot dynamic model to reduce a difference between the simulated joint physical parameter values and the corresponding joint physical parameter measurements.

    ROBOTIC CONTROL BASED ON 3D BOUNDING SHAPE, FOR AN OBJECT, GENERATED USING EDGE-DEPTH VALUES FOR THE OBJECT
    4.
    发明申请
    ROBOTIC CONTROL BASED ON 3D BOUNDING SHAPE, FOR AN OBJECT, GENERATED USING EDGE-DEPTH VALUES FOR THE OBJECT 审中-公开

    公开(公告)号：US20200376675A1

    公开(公告)日：2020-12-03

    申请号：US16424363

    申请日：2019-05-28

    Applicant: X Development LLC

    Inventor： Yunfei Bai ,  Yuanzheng Gong

    IPC: B25J9/16 ,  G06T7/521 ,  G06T7/13 ,  G06T7/12 ,  G06T5/00 ,  H04N5/247 ,  G06K9/62

    Abstract: Generating edge-depth values for an object, utilizing the edge-depth values in generating a 3D point cloud for the object, and utilizing the generated 3D point cloud for generating a 3D bounding shape (e.g., 3D bounding box) for the object. Edge-depth values for an object are depth values that are determined from frame(s) of vision data (e.g., left/right images) that captures the object, and that are determined to correspond to an edge of the object (an edge from the perspective of frame(s) of vision data). Techniques that utilize edge-depth values for an object (exclusively, or in combination with other depth values for the object) in generating 3D bounding shapes can enable accurate 3D bounding shapes to be generated for partially or fully transparent objects. Such increased accuracy 3D bounding shapes directly improve performance of a robot that utilizes the 3D bounding shapes in performing various tasks.

    Mitigating reality gap through optimization of simulated hardware parameter(s) of simulated robot
    5.
    发明授权
    Mitigating reality gap through optimization of simulated hardware parameter(s) of simulated robot 有权

    公开(公告)号：US11707840B1

    公开(公告)日：2023-07-25

    申请号：US17535373

    申请日：2021-11-24

    Applicant: X Development LLC

    Inventor： Yunfei Bai ,  Elmar Mair ,  Yuchen Wu ,  Ian Wilkes ,  Max Moroz ,  Weidan Wu

    IPC: G06F17/00 ,  B25J9/16 ,  G05B13/02 ,  G05B13/04

    CPC classification number: B25J9/163 ,  B25J9/1653 ,  G05B13/0265 ,  G05B13/042

    Abstract: Mitigating the reality gap through optimization of one or more simulated hardware parameters for simulated hardware components of a simulated robot. Implementations generate and store real navigation data instances that are each based on a corresponding episode of locomotion of a real robot. A real navigation data instance can include a sequence of velocity control instances generated to control a real robot during a real episode of locomotion of the real robot, and one or more ground truth values, where each of the ground truth values is a measured value of a corresponding property of the real robot (e.g., pose). The velocity control instances can be applied to a simulated robot, and one or more losses can be generated based on comparing the ground truth value(s) to corresponding simulated value(s) generated from applying the velocity control instances to the simulated robot. The simulated hardware parameters and environmental parameters can be optimized based on the loss(es).

    Generating simulated training examples for training of machine learning model used for robot control
    6.
    发明授权
    Generating simulated training examples for training of machine learning model used for robot control 有权

    公开(公告)号：US11494632B1

    公开(公告)日：2022-11-08

    申请号：US15835357

    申请日：2017-12-07

    Applicant: X Development LLC

    Inventor： Yunfei Bai

    IPC: G05B13/02 ,  G06N3/08 ,  B25J9/16 ,  G06N3/04

    Abstract: Implementations are directed to generating simulated training examples for training of a machine learning model, training the machine learning model based at least in part on the simulated training examples, and/or using the trained machine learning model in control of at least one real-world physical robot. Implementations are additionally or alternatively directed to performing one or more iterations of quantifying a “reality gap” for a robotic simulator and adapting parameter(s) for the robotic simulator based on the determined reality gap. The robotic simulator with the adapted parameter(s) can further be utilized to generate simulated training examples when the reality gap of one or more iterations satisfies one or more criteria.

    MACHINE LEARNING METHODS AND APPARATUS FOR ROBOTIC MANIPULATION AND THAT UTILIZE MULTI-TASK DOMAIN ADAPTATION
    8.
    发明申请
    MACHINE LEARNING METHODS AND APPARATUS FOR ROBOTIC MANIPULATION AND THAT UTILIZE MULTI-TASK DOMAIN ADAPTATION 审中-公开

    公开(公告)号：US20190084151A1

    公开(公告)日：2019-03-21

    申请号：US15913212

    申请日：2018-03-06

    Applicant: X Development LLC

    Inventor： Yunfei Bai ,  Kuan Fang ,  Stefan Hinterstoisser ,  Mrinal Kalakrishnan

    IPC: B25J9/16

    Abstract: Implementations are directed to training a machine learning model that, once trained, is used in performance of robotic grasping and/or other manipulation task(s) by a robot. The model can be trained using simulated training examples that are based on simulated data that is based on simulated robot(s) attempting simulated manipulations of various simulated objects. At least portions of the model can also be trained based on real training examples that are based on data from real-world physical robots attempting manipulations of various objects. The simulated training examples can be utilized to train the model to predict an output that can be utilized in a particular task—and the real training examples used to adapt at least a portion of the model to the real-world domain can be tailored to a distinct task. In some implementations, domain-adversarial similarity losses are determined during training, and utilized to regularize at least portion(s) of the model.

    Mitigating reality gap through modification of simulated state data of robotic simulator
    10.
    发明授权
    Mitigating reality gap through modification of simulated state data of robotic simulator 有权

    公开(公告)号：US11461589B1

    公开(公告)日：2022-10-04

    申请号：US16267077

    申请日：2019-02-04

    Applicant: X Development LLC

    Inventor： Yunfei Bai

    IPC: G06K9/62 ,  G06N3/04 ,  B25J9/16 ,  G06N3/08 ,  G06N20/00

    Abstract: Mitigating the reality gap through training and utilization of at least one difference model. The difference model can be utilized to generate, for each of a plurality of instances of simulated state data generated by a robotic simulator, a corresponding instance of modified simulated state data. The difference model is trained so that a generated modified instance of simulated state data is closer to “real world data” than is a corresponding initial instance of simulated state data. Accordingly, the difference model can be utilized to mitigate the reality gap through modification of initially generated simulated state data, to make it more accurately reflect what would occur in a real environment. Moreover, the difference representation from the difference model can be used as input to the control policy to adapt the control learned from simulator to the real environment.

Patent Agency Ranking