Applied Materials, Inc.

X Development LLC

Mineral Earth Sciences LLC

Deere + Company

Kangkang Wang

Ludovic Godet

Benjamin B Riordon

Zhiqiang Yuan

James D Strassner

Yaseer Arafath Ahamed

Lianghao Li

Yige Gao

Bodi Yuan

Wei-Sheng Lei

Visweswaren Sivaramakrishnan

Mahendran Chidambaram

Amita Joshi

Xiaopei Deng

Alexander Ngai

Zachary Beaver

Hong Wu

Thinh Nguyen

Zihao Li

Neal Ricks

Embodiments described herein include a waveguide combiner having an edge coated with an optically absorbent composition and a method of coating the edge of the waveguide combiner with the optically absorbent composition. The optically absorbent composition includes one or more types of nanoparticles or microparticles, at least one of one or more dyes or one or more pigments, and a polymer matrix of one or more binders. The method includes producing an optically absorbent formulation. The optically absorbent formulation includes one or more types of particles, at least one of one or more dyes or one or more pigments, one or more binders, and one or more solvents. The optically absorbent formulation is applied on an edge of a waveguide combiner using an edge blackening tool. The formulation is cured with radiation to form the optically absorbent composition.

High index edge blackening material

Embodiments of the present disclosure generally relate to optical devices. More specifically, embodiments described herein relate to apparatuses and methods for gripping optical devices. In an embodiment, an apparatus for gripping an optical device includes a base coupled to a proximal end of a stem extending from a bottom surface of the base. The apparatus also includes a plurality of arms movably coupled to the bottom surface of the base. The plurality of arms are coupled to an actuator operable to move the plurality of arms laterally along a X-Y plane parallel to the bottom surface of the base. In some embodiments, the apparatus includes a suction pad operable to provide a non-contact vertical suction force.

Apparatuses and methods for handling optical devices of varying geometries

Implementations are described herein for performing depth estimation in the agricultural domain, including generating synthetic training data. In various implementations, one or more three-dimensional synthetic plants may be generated in in a three-dimensional space, wherein the one or more three-dimensional synthetic plants include homogenous and densely-distributed synthetic plant parts. The plurality of three-dimensional synthetic plants may be projected onto two-dimensional planes from first and second perspectives in the three-dimensional space to form a pair of synthetic stereoscopic images. The first and second synthetic stereoscopic images of the pair may be annotated to create a mapping between the individual synthetic plant parts across the first synthetic stereoscopic images. A feature matching machine learning model may be trained based on the mapping.

Sparse and/or dense depth estimation from stereoscopic imaging

An optical device coating assembly is provided. The optical device coating assembly includes a substrate support operable to retain an optical device substrate. The coating assembly further includes a first actuator connected to the substrate support. The first actuator is configured to rotate the substrate support. The coating assembly includes a holder configured to hold a coating applicator against an edge of the optical device substrate when the optical device substrate is rotated on the substrate support and a second actuator operable to apply a force on the holder in a direction towards the substrate support. The second actuator is a constant force actuator.

Edge blackening for optical devices

A method and apparatus for substrate dicing are described. The method includes utilizing a laser to dice a substrate along a dicing path to form a perforated line around each device within the substrate. The dicing path is created by exposing the substrate to bursts of laser pulses at different locations around each device. The laser pulses are delivered to the substrate and may have a pulse repetition frequency of greater than about 25 MHz, a pulse width of less than about 15 picoseconds, and a laser wavelength of about 1.0 μm to about 5 μm.

Laser dicing glass wafers using advanced laser sources

Implementations are described herein for automatically labeling synthetic plant parts in synthetic training images, where the synthetic training images and corresponding labels can be used as training data for training machine learning models to detect, segment, and/or classify various parts of plants in digital images. In various implementations, a digital image may be obtained that captures an area. The synthetic training image may be generated to depict one or more three-dimensional synthetic plants in the area. In many implementations, a plant mask, identifying individual plants as a whole in the synthetic training image, as well as a part mask, uniquely identifying one or more parts of the synthetic plant models, can be overlaid on the synthetic training image to label the one or more parts of the synthetic plant models.

Generating labeled synthetic training data

Embodiments described herein provide for devices and methods for retaining optical devices. The devices and methods described herein provide for retention of the substrate without contacting sensitive portions of the substrate. The devices and methods utilize retention pads or vacuum pins to contact the exclusion zones i.e., inactive areas of the substrate to retain the substrate and prevent the substrate from moving laterally. Additionally, a holding force retains the substrate in the vertical direction, without contacting the substrate. The methods provide for adjusting the devices to account for multiple geometries of the substrate. The methods further provide for adjusting the devices, such as adjusting a gap between the optical device and a suction pad, to alter the holding force of the devices on the optical devices.

Minimal contact gripping of thin optical devices

Embodiments of the present disclosure relate to a carrier mechanism for retaining optical devices. The carrier mechanism includes adjacent tray assemblies stacked such that a plurality of optical device lenses are retained therebetween. The carrier mechanism retains the plurality of optical device lenses without damaging the plurality of optical device lenses by contacting corners of the optical device lenses. The plurality of optical device lenses are retained with a plurality of support pins and a plurality of capture pins disposed in the tray assemblies. Each tray includes a plurality of openings corresponding to the plurality of optical device lenses such that fluids may contact the plurality of optical device lenses. The carrier mechanism may be utilized in multiple processing methods of the plurality of optical device lenses.

Carrier mechanism for cleaning and handling

Implementations are described herein for automatically generating synthetic training images that are usable, for instance, as training data for training machine learning models to detect and/or classify various types of plant diseases at various stages in digital images. In various implementations, one or more environmental features associated with an agricultural area may be retrieved. One or more synthetic plant models may be generated to visually simulate one or more stages of a progressive plant disease, taking into account the one or more environmental features associated with the agricultural area. The one or more synthetic plant models may be graphically incorporated into a synthetic training image that depicts the agricultural area.

Generating and using synthetic training data for plant disease detection

Implementations are described herein for automatically generating quasi-realistic synthetic training images that are usable as training data for training machine learning models to perceive various types of plant traits in digital images. In various implementations, multiple labeled simulated images may be generated, each depicting simulated and labeled instance(s) of a plant having a targeted plant trait. In some implementations, the generating may include stochastically selecting features of the simulated instances of plants from a collection of plant assets associated with the targeted plant trait. The collection of plant assets may be obtained from ground truth digital image(s). In some implementations, the ground truth digital image(s) may depict real-life instances of plants having the target plant trait. The plurality of labeled simulated images may be processed using a trained generator model to generate a plurality of quasi-realistic synthetic training images, each depicting quasi-realistic and labeled instance(s) of the targeted plant trait.

Generating quasi-realistic synthetic training data for use with machine learning models

Implementations are described herein for automatically generating synthetic training images that are usable as training data for training machine learning models to detect, segment, and/or classify various types of plants in digital images. In various implementations, a digital image may be obtained that captures an area. The digital image may depict the area under a lighting condition that existed in the area when a camera captured the digital image. Based at least in part on an agricultural history of the area, a plurality of three-dimensional synthetic plants may be generated. The synthetic training image may then be generated to depict the plurality of three-dimensional synthetic plants in the area. In some implementations, the generating may include graphically incorporating the plurality of three-dimensional synthetic plants with the digital image based on the lighting condition.

Growing community of inventors

San Jose, CA, United States of America

Kangkang Wang