公开(公告)号：US20210326694A1

公开(公告)日：2021-10-21

申请号：US16852944

申请日：2020-04-20

Applicant: Nvidia Corporation

Inventor： Jialiang Wang ,  Varun Jampani ,  Stan Birchfield ,  Charles Loop ,  Jan Kautz

IPC: G06N3/08 ,  G06N3/04

Abstract: Apparatuses, systems, and techniques are presented to determine distance for one or more objects. In at least one embodiment, a disparity network is trained to determine distance data from input stereoscopic images using a loss function that includes at least one of a gradient loss term and an occlusion loss term.

公开(公告)号：US11080590B2

公开(公告)日：2021-08-03

申请号：US16356439

申请日：2019-03-18

Applicant: NVIDIA Corporation

Inventor： Nikolai Smolyanskiy ,  Alexey Kamenev ,  Stan Birchfield

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/10 ,  G01S17/00 ,  G06T7/00 ,  G06T7/593 ,  G06T1/20 ,  G06K9/62 ,  G06N3/063 ,  G01S17/86 ,  G01S17/89

Abstract: Various examples of the present disclosure include a stereoscopic deep neural network (DNN) that produces accurate and reliable results in real-time. Both LIDAR data (supervised training) and photometric error (unsupervised training) may be used to train the DNN in a semi-supervised manner. The stereoscopic DNN may use an exponential linear unit (ELU) activation function to increase processing speeds, as well as a machine learned argmax function that may include a plurality of convolutional layers having trainable parameters to account for context. The stereoscopic DNN may further include layers having an encoder/decoder architecture, where the encoder portion of the layers may include a combination of three-dimensional convolutional layers followed by two-dimensional convolutional layers.

公开(公告)号：US20190228495A1

公开(公告)日：2019-07-25

申请号：US16255038

申请日：2019-01-23

Applicant: Nvidia Corporation

Inventor： Jonathan Tremblay ,  Stan Birchfield ,  Stephen Tyree ,  Thang To ,  Jan Kautz ,  Artem Molchanov

IPC: G06T1/00 ,  G06T7/73 ,  B25J9/16

Abstract: Various embodiments enable a robot, or other autonomous or semi-autonomous device or system, to receive data involving the performance of a task in the physical world. The data can be provided as input to a perception network to infer a set of percepts about the task, which can correspond to relationships between objects observed during the performance. The percepts can be provided as input to a plan generation network, which can infer a set of actions as part of a plan. Each action can correspond to one of the observed relationships. The plan can be reviewed and any corrections made, either manually or through another demonstration of the task. Once the plan is verified as correct, the plan (and any related data) can be provided as input to an execution network that can infer instructions to cause the robot, and/or another robot, to perform the task.