Zoox, Inc.

Aprio Technologies, Inc.

Siebel Systems, Inc.

Tela Innovations, Inc.

Xin Wang

Yi Xu

Sarah Tariq

Kratarth Goel

Shao-Po Wu

Vasiliy Karasev

Oytun Ulutan

Hongbo Tang

Meg Hung

Alexander Goldstein

Tarri E Furlong

Ashley Grant Stirrup

Daniel T Chang

Pasan Rukmal Sirisena

Xinyu Xu

Marc Verbeek

Steve Apfelberg

Ajay Sabhlok

Martin Renaud

Mark Pilloff

Tao Gui

Charles Shagong

Techniques for performing computer vision operations for a vehicle using image data of an environment of the vehicle are described herein. In some cases, a vehicle (e.g., an autonomous vehicle) can determine a predicted position (including a predicted depth) and/or a predicted trajectory for an object in the vehicle environment based on data generated by projecting a map object described by the map data for a vehicle environment to image data of the vehicle environment.

Computer vision techniques using projections of map data into image data

Techniques for detecting attributes and/or gestures associated with pedestrians in an environment are described herein. The techniques may include receiving sensor data associated with a pedestrian in an environment of a vehicle and inputting the sensor data into a machine-learned model that is configured to determine a gesture and/or an attribute of the pedestrian. Based on the input data, an output may be received from the machine-learned model that indicates the gesture and/or the attribute of the pedestrian and the vehicle may be controlled based at least in part on the gesture and/or the attribute of the pedestrian. The techniques may also include training the machine-learned model to detect the attribute and/or the gesture of the pedestrian.

Pedestrian attribute and gesture detection

Techniques for detecting door states associated with vehicles in an environment are described herein. The techniques may include receiving sensor data associated with a first vehicle in an environment and inputting the sensor data into a machine-learned model that is configured to determine a state of a door of the first vehicle. Based on the input data, an output may be received from the machine-learned model that indicates the state of the door of the first vehicle. Based on the state of the door of the first vehicle, a trajectory of a second vehicle may be controlled. The techniques may also include training the machine-learned model to detect door states of vehicles.

Vehicle door state detection

Machine-learned model training for pedestrian attribute and gesture detection

A method, system, and article of manufacture for defining and managing instances of time-based organization hierarchies, and for monitoring achievement and attainment, and calculating compensation for individuals and/or groups within instances of the time-based organization hierarchies are disclosed herein. In one embodiment, a user may define and/or manage one or more instances of the time-based organization hierarchy via a user interface generated on a client. Moreover, and in response to a sales data input corresponding to a transaction, an achievement and attainment monitoring process may then be executed to accumulate transaction data in one or more achievement containers, and to compile achievement containers from a specified attainment period to calculate a user's attainment. In addition, an embodiment also provides for implementation of a compensation calculation process that may utilize the transaction data accumulated in the achievement containers to calculate an individual's compensation for a specified compensation period.

Method and system for monitoring achievement and attainment and calculating compensation via time-based organization hierarchies

Intermediate resolution-enhancement state layouts are generated based upon an original non-resolution enhanced layout of an integrated circuit and an associated resolution-enhanced layout. The intermediate resolution-enhancement state layout includes fragments corresponding to parts of the original layout and biases associated with the fragments, where the biases indicate distances between the fragments and the resolution-enhanced layout. The fragments are also assigned attributes such as fragment type, fragment location, and biases. The intermediate resolution-enhancement state layouts can be combined to generate the layout for a full chip IC. Two or more intermediate resolution-enhancement state layouts are assembled and are locally reconverged to adjust the resolution enhancement associated with the intermediate resolution-enhancement state layouts and obtain the intermediate resolution-enhancement state layouts for the full IC.

Intermediate layout for resolution enhancement in semiconductor fabrication

Transient edges are used to define shapes in an integrated circuit layout for optical proximity correction. A first variation of the shape includes a first edge, a second edge satisfying an edge transition angle condition in relation to the first edge, and one or more first transition edges connected between the first edge and the second edge. A second variation of the shape includes a third edge, a fourth edge satisfying the same edge transition angle condition in relation to the third edge, and one or more second transition edges connected between the third edge and the fourth edge. Although the first transition edges are different from the second transition edges, both the first and second variations of the shape are identified as having the same shape, thereby allowing flexibility and efficiency in the shape identification process for optical proximity correction.

Flexible shape identification for optical proximity correction in semiconductor fabrication

Growing community of inventors

Sunnyvale, CA, United States of America

Xin Wang