公开(公告)号：US11902705B2

公开(公告)日：2024-02-13

申请号：US16558620

申请日：2019-09-03

Applicant: Nvidia Corporation

Inventor： Kevin Shih ,  Aysegul Dundar ,  Animesh Garg ,  Robert Pottorff ,  Andrew Tao ,  Bryan Catanzaro

IPC: G06N3/04 ,  H04N7/01 ,  G06N3/08 ,  G06F18/214 ,  G06F18/21 ,  G06N3/044 ,  G06N3/045

CPC classification number: H04N7/0135 ,  G06F18/214 ,  G06F18/217 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to enhance video are disclosed. In at least one embodiment, one or more neural networks are used to create, from a first video, a second video having one or more additional video frames.

公开(公告)号：US12109701B2

公开(公告)日：2024-10-08

申请号：US16780465

申请日：2020-02-03

Applicant: NVIDIA Corporation

Inventor： Jonathan Tremblay ,  Dieter Fox ,  Michelle Lee ,  Carlos Florensa ,  Nathan Donald Ratliff ,  Animesh Garg ,  Fabio Tozeto Ramos

IPC: B25J9/16 ,  G05B13/02 ,  G05B13/04 ,  G06N3/08 ,  G06N5/046 ,  G06N20/00

CPC classification number: B25J9/163 ,  B25J9/1661 ,  B25J9/1664 ,  B25J9/1697 ,  G05B13/027 ,  G05B13/04 ,  G06N3/08 ,  G06N5/046 ,  G06N20/00

Abstract: A robot is controlled using a combination of model-based and model-free control methods. In some examples, the model-based method uses a physical model of the environment around the robot to guide the robot. The physical model is oriented using a perception system such as a camera. Characteristics of the perception system may be are used to determine an uncertainty for the model. Based at least in part on this uncertainty, the system transitions from the model-based method to a model-free method where, in some embodiments, information provided directly from the perception system is used to direct the robot without reliance on the physical model.

公开(公告)号：US20240095077A1

公开(公告)日：2024-03-21

申请号：US18122594

申请日：2023-03-16

Applicant: NVIDIA Corporation

Inventor： Ishika Singh ,  Arsalan Mousavian ,  Ankit Goyal ,  Danfei Xu ,  Jonathan Tremblay ,  Dieter Fox ,  Animesh Garg ,  Valts Blukis

IPC: G06F9/50 ,  G06N20/00

CPC classification number: G06F9/5027 ,  G06N20/00

Abstract: Apparatuses, systems, and techniques to generate a prompt for one or more machine learning processes. In at least one embodiment, the machine learning process(es) generate(s) a plan to perform a task (identified in the prompt) that is to be performed by an agent (real world or virtual).

公开(公告)号：US20220180528A1

公开(公告)日：2022-06-09

申请号：US17678666

申请日：2022-02-23

Applicant: NVIDIA Corporation

Inventor： Aysegul Dundar ,  Kevin Jonathan Shih ,  Animesh Garg ,  Robert Thomas Pottorff ,  Andrew Tao ,  Bryan Christopher Catanzaro

IPC: G06T7/194 ,  G06N20/00 ,  G06N5/04 ,  G06T7/70 ,  G06N3/08 ,  G06V20/20

Abstract: Apparatuses, systems, and techniques to perform unsupervised keypoint or landmark learning using one or more neural networks. In at least one embodiment, one or more neural networks use pose and appearance information to construct a foreground and a background, which are then used to reconstruct an input image and determine loss values to train the one or more neural networks.

公开(公告)号：US20210081752A1

公开(公告)日：2021-03-18

申请号：US16931211

申请日：2020-07-16

Applicant: NVIDIA Corporation

Inventor： Yu-Wei Chao ,  De-An Huang ,  Christopher Jason Paxton ,  Animesh Garg ,  Dieter Fox

IPC: G06N3/00 ,  G06N20/00

Abstract: Apparatuses, systems, and techniques to identify a goal of a demonstration. In at least one embodiment, video data of a demonstration is analyzed to identify a goal. Object trajectories identified in the video data are analyzed with respect to a task predicate satisfied by a respective object trajectory, and with respect to motion predicate. Analysis of the trajectory with respect to the motion predicate is used to assess intentionality of a trajectory with respect to the goal.

公开(公告)号：US20230398686A1

公开(公告)日：2023-12-14

申请号：US18114146

申请日：2023-02-24

Applicant: NVIDIA Corporation

Inventor： Fabio Tozeto Ramos ,  Animesh Garg ,  Krishna Murthy Jatavallabhula ,  Miles Macklin

IPC: B25J9/16

CPC classification number: B25J9/1664 ,  B25J9/163 ,  B25J9/1671

Abstract: Apparatuses, systems, and techniques to update a machine learning model associated with an object. In at least one embodiment, the machine learning model is updated based at least in part on, for example, one or more distributions associated with the machine learning model.

公开(公告)号：US20220374723A1

公开(公告)日：2022-11-24

申请号：US17316564

申请日：2021-05-10

Applicant: NVIDIA Corporation

Inventor： Valts Blukis ,  Christopher Jason Paxton ,  Animesh Garg ,  Dieter Fox

IPC: G06N5/00 ,  G06F16/332 ,  G06K9/62 ,  G06N3/08

Abstract: Apparatuses, systems, and techniques to perform a language-guided distributional tree search based at least in part on a natural language task. In at least one embodiment, a tree search is performed using one or more neural networks to determine an action to be performed by an autonomous agent.

公开(公告)号：US20220012596A1

公开(公告)日：2022-01-13

申请号：US16925085

申请日：2020-07-09

Applicant: NVIDIA Corporation

Inventor： Weili Nie ,  Tero Tapani Karras ,  Animesh Garg ,  Shoubhik Debnath ,  Anjul Patney ,  Anima Anandkumar

IPC: G06N3/08 ,  G06N3/063 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques used to train one or more neural networks to generate images comprising one or more features. In at least one embodiment, one or more neural networks are trained to determine one or more styles for an input image and then generate features associated with said one or more styles in an output image.

公开(公告)号：US20210146531A1

公开(公告)日：2021-05-20

申请号：US16780465

申请日：2020-02-03

Applicant: NVIDIA Corporation

Inventor： Jonathan Tremblay ,  Dieter Fox ,  Michelle Lee ,  Carlos Florensa ,  Nathan Donald Ratliff ,  Animesh Garg ,  Fabio Tozeto Ramos

IPC: B25J9/16 ,  G05B13/02 ,  G06N3/08 ,  G05B13/04 ,  G06N5/04 ,  G06N20/00

Abstract: A robot is controlled using a combination of model-based and model-free control methods. In some examples, the model-based method uses a physical model of the environment around the robot to guide the robot. The physical model is oriented using a perception system such as a camera. Characteristics of the perception system may be are used to determine an uncertainty for the model. Based at least in part on this uncertainty, the system transitions from the model-based method to a model-free method where, in some embodiments, information provided directly from the perception system is used to direct the robot without reliance on the physical model.

公开(公告)号：US11958529B2

公开(公告)日：2024-04-16

申请号：US16998941

申请日：2020-08-20

Applicant: NVIDIA Corporation

Inventor： Ajay Uday Mandlekar ,  Fabio Tozeto Ramos ,  Byron Boots ,  Animesh Garg ,  Dieter Fox

IPC: B62D15/02 ,  B25J1/02 ,  B60W30/06 ,  B60W60/00 ,  G05B13/02 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08

CPC classification number: B62D15/0285 ,  B25J1/02 ,  B60W30/06 ,  B60W60/0025 ,  G05B13/027 ,  G06N3/045 ,  G06N3/08

Abstract: A framework for offline learning from a set of diverse and suboptimal demonstrations operates by selectively imitating local sequences from the dataset. At least one embodiment recovers performant policies from large manipulation datasets by decomposing the problem into a goal-conditioned imitation and a high-level goal selection mechanism.