公开(公告)号：US20240300099A1

公开(公告)日：2024-09-12

申请号：US18489789

申请日：2023-10-18

Applicant: NVIDIA CORPORATION

Inventor： Bingjie TANG ,  Yashraj Shyam NARANG ,  Dieter FOX ,  Fabio TOZETO RAMOS

IPC: B25J9/16

CPC classification number: B25J9/163 ,  B25J9/1605 ,  B25J9/1653

Abstract: One embodiment of a method for training a machine learning model to control a robot includes causing a model of the robot to move within a simulation based on one or more outputs of the machine learning model, computing an error within the simulation, computing at least one of a reward or an observation based on the error, and updating one or more parameters of the machine learning model based on the at least one of a reward or an observation.

公开(公告)号：US20240095527A1

公开(公告)日：2024-03-21

申请号：US18448049

申请日：2023-08-10

Applicant: NVIDIA CORPORATION

Inventor： Ankur HANDA ,  Gavriel STATE ,  Arthur David ALLSHIRE ,  Dieter FOX ,  Jean-Francois Victor LAFLECHE ,  Jingzhou LIU ,  Viktor MAKOVIICHUK ,  Yashraj Shyam NARANG ,  Aleksei Vladimirovich PETRENKO ,  Ritvik SINGH ,  Balakumar SUNDARALINGAM ,  Karl VAN WYK ,  Alexander ZHURKEVICH

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: Systems and techniques are described related to training one or more machine learning models for use in control of a robot. In at least one embodiment, one or more machine learning models are trained based at least on simulations of the robot and renderings of such simulations—which may be performed using one or more ray tracing algorithms, operations, or techniques.

公开(公告)号：US20230321822A1

公开(公告)日：2023-10-12

申请号：US18074387

申请日：2022-12-02

Applicant: NVIDIA CORPORATION

Inventor： Yashraj Shyam NARANG ,  Kier STOREY ,  Iretiayo AKINOLA ,  Dieter FOX ,  Kelly GUO ,  Ankur HANDA ,  Fengyun LU ,  Miles MACKLIN ,  Adam MORAVANSZKY ,  Philipp REIST ,  Gavriel STATE ,  Lukasz WAWRZYNIAK

IPC: B25J9/16

CPC classification number: B25J9/163 ,  B25J9/161 ,  B25J9/1671 ,  B25J9/1666

Abstract: One embodiment of a method for controlling a robot includes performing a plurality of simulations of a robot interacting with one or more objects represented by one or more signed distance functions (SDFs), where performing the plurality of simulations comprises reducing a number of contacts between the one or more objects that are being simulated, and updating one or more parameters of a machine learning model based on the plurality of simulations to generate a trained machine learning model.

公开(公告)号：US20230191605A1

公开(公告)日：2023-06-22

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

CPC classification number: B25J9/1671 ,  B25J9/163 ,  B25J9/161 ,  B25J9/1689

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.

公开(公告)号：US20230191596A1

公开(公告)日：2023-06-22

申请号：US17695753

申请日：2022-03-15

Applicant: NVIDIA CORPORATION

Inventor： Ankur HANDA ,  Iretiayo AKINOLA ,  Dieter FOX ,  Yashraj Shyam NARANG

IPC: B25J9/16

CPC classification number: B25J9/163 ,  B25J9/161 ,  B25J9/1671 ,  B25J9/1612

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.

公开(公告)号：US20240338598A1

公开(公告)日：2024-10-10

申请号：US18606938

申请日：2024-03-15

Applicant: NVIDIA CORPORATION

Inventor： Caelan Reed GARRETT ,  Fabio TOZETO RAMOS ,  Iretiayo AKINOLA ,  Alperen DEGIRMENCI ,  Clemens EPPNER ,  Dieter FOX ,  Tucker Ryer HERMANS ,  Ajay Uday MANDLEKAR ,  Arsalan MOUSAVIAN ,  Yashraj Shyam NARANG ,  Rowland Wilde O'FLAHERTY ,  Balakumar SUNDARALINGAM ,  Wei YANG

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: One embodiment of a method for generating simulation data to train a machine learning model includes generating a plurality of simulation environments based on a user input, and for each simulation environment included in the plurality of simulation environments: generating a plurality of tasks for a robot to perform within the simulation environment, performing one or more operations to determine a plurality of robot trajectories for performing the plurality of tasks, and generating simulation data for training a machine learning model by performing one or more operations to simulate the robot moving within the simulation environment according to the plurality of trajectories.

公开(公告)号：US20240300100A1

公开(公告)日：2024-09-12

申请号：US18490630

申请日：2023-10-19

Applicant: NVIDIA CORPORATION

Inventor： Yashraj Shyam NARANG ,  Ankur HANDA ,  Karl VAN WYK ,  Dieter FOX ,  Michael Andres LIN ,  Fabio TOZETO RAMOS

IPC: B25J9/16

CPC classification number: B25J9/163 ,  B25J9/1653 ,  B25J9/1664

Abstract: One embodiment of a method for controlling a robot includes receiving sensor data indicating a state of the robot, generating an action based on the sensor data and a trained machine learning model, computing a target state of the robot based on the action and a previous target state of the robot, and causing the robot to move based on the target state of the robot.