Nvidia Corporation

Anima Anandkumar

Stephen William Keckler

Timothy Tsai

Iuri Frosio

Yuke Zhu

Siva Kumar Sastry Hari

Zahra Ghodsi

Jonathan Tremblay

Alejandro Jose Troccoli

Fabio Tozeto Ramos

Guanya Shi

Jan Kautz

Sifei Liu

Zhiding Yu

Rui Huang

Guilin Liu

Wonmin Byeon

Thomas Michael Breuel

Youngwoon Lee

A manipulation task may include operations performed by one or more manipulation entities on one or more objects. This manipulation task may be broken down into a plurality of sequential sub-tasks (policies). These policies may be fine-tuned so that a terminal state distribution of a given policy matches an initial state distribution of another policy that immediately follows the given policy within the plurality of policies. The fine-tuned plurality of policies may then be chained together and implemented within a manipulation environment.

Fine-tuning policies to facilitate chaining

Techniques to generate driving scenarios for autonomous vehicles characterize a path in a driving scenario according to metrics such as narrowness and effort. Nodes of the path are assigned a time for action to avoid collision from the node. The generated scenarios may be simulated in a computer.

Adversarial scenarios for safety testing of autonomous vehicles

Apparatuses, systems, and techniques generate poses of an object based on image data of the object obtained from a first viewpoint of the object and a second viewpoint of the object. The poses can be evaluated to determine a portion of the image data usable by an estimator to generate a pose of the object.

Data selection based on uncertainty quantification

Apparatuses, systems, and techniques generate poses of an object based on data of the object observed from a first viewpoint and a second viewpoint. The poses can be evaluated to determine a portion of the data usable by an estimator to generate a pose of the object.

The disclosure provides a learning framework that unifies both semantic segmentation and semantic edge detection. A learnable recurrent message passing layer is disclosed where semantic edges are considered as explicitly learned gating signals to refine segmentation and improve dense prediction quality by finding compact structures for message paths. The disclosure includes a method for coupled segmentation and edge learning. In one example, the method includes: (1) receiving an input image, (2) generating, from the input image, a semantic feature map, an affinity map, and a semantic edge map from a single backbone network of a convolutional neural network (CNN), and (3) producing a refined semantic feature map by smoothing pixels of the semantic feature map using spatial propagation, and controlling the smoothing using both affinity values from the affinity map and edge values from the semantic edge map.

Image processing using coupled segmentation and edge learning

Techniques to characterize driving scenarios for autonomous vehicles characterize a path in a driving scenario according to metrics such as narrowness and effort. The scenarios may be characterized using a tree-based or tensor-based approach.

Tensor-based driving scenario characterization

Growing community of inventors

Santa Clara, CA, United States of America

Anima Anandkumar