The Boeing Company

Theboeing Company

Nick Shadbeh Evans

Bradley James Mitchell

Mark Stewart Wilenski

Faraón Torres

Samuel F Harrison

Michael Patrick Kozar

Tyler Charles Staudinger

Amir Afrasiabi

Deepak Khosla

Kevin Scott Callahan

Stephen G Dame

Hayden S Osborn

Eerik J Helmick

Damien O Martin

Ryan G Ziegler

Lars Eric Blacken

Matthew A Moser

Brian Kenyon Rupnik

Dragos Dorin Margineantu

Grace L Duncan

Eric Raymond Muir

Keith M Cutler

Brian T Whitehead

James Jason Salmon

Zachary D Jorgensen

Isaac Chang

Leon Nguyen

Aphea Ann Thornton

Joshua David Kalin

Jasper P Corleis

Patrick William O'Neill

Michelle D Warren

William K Leach

Cullen W Billhartz

Vandan Patel

Faraon Torres

Dinh X Tran

Mark Gordon Sellars

Michael Joseph Surface

Neil Reza Shadbeh Evans

Mary Karroqe

David S Wright

Eerick J Helmick

Ciro J Grijalva

An apparatus for identifying objects receives a dataset comprising an image having first real image features; trains a neural network to recognize the first real image features in the received dataset; and performs a synthetic image augmentation to generate synthetic image features corresponding to the first real image features in the received dataset using the neural network. The synthetic image augmentation allows for improved training of a computer vision function for recognizing second real image features, corresponding to the synthetic image features, in a real-world environment.

Unpaired image-to-image translation using a generative adversarial network (GAN)

Certain aspects of the present disclosure provide techniques for autonomous image acquisition. This includes determining a plurality of two-dimensional image perspectives for a plurality of image capture devices, and comparing the plurality of two-dimensional image perspectives with a generated two-dimensional representation of a target object, where the two-dimensional representation is generated based on a three-dimensional model of the target object. This further includes automatically moving at least one of the plurality of image capture devices, based on the comparing, to increase a portion of the target object captured by the plurality of image capture devices.

Autonomous image acquisition systems for production and environment monitoring and event detection

Systems for preparing, training, and deploying a machine learning algorithm for making medical condition state determinations include at least one processing unit that includes the machine learning algorithm. The at least one processing unit is programmed to receive image input from an imaging device, receive patient health data, encode the patient health data to convert the patient health data to encoded patient health data, and transmit the encoded patient health data into the machine learning algorithm. Systems are configured to make a medical condition state determination based on the image input and the encoded patient health data, via the machine learning algorithm, and provide visual output for the medical condition state determination via a display device such that the visual output may be augmented with the patient health data. Dynamic state information also may be input to the machine learning algorithm and used to make medical condition state determinations.

Machine learning algorithms for detecting medical conditions, related systems, and related methods

A method is provided for supporting an aircraft approaching a runway on an airfield. The method includes receiving a sequence of images of the airfield, captured by a camera onboard the aircraft approaching the runway. For at least one image of the sequence of images, the method includes applying the image(s) to a machine learning model trained to predict a pose of the aircraft relative to the runway. The machine learning model is configured to map the image(s) to the pose based on a training set of labeled images with respective ground truth poses of the aircraft relative to the runway. The pose is output as a current pose estimate of the aircraft relative to the runway for use in at least one of monitoring the current pose estimate, generating an alert based on the current pose estimate, or guidance or control of the aircraft on a final approach.

Determining a current pose estimate of an aircraft relative to a runway to support the aircraft on approach

Systems and methods of aligning removable sensors mounted on a vehicle based upon sensor output of such sensors are described. Sensor output is collected from a removable sensor (e.g., a digital camera), and a representation of such sensor output is generated (e.g., a digital image). The representation of the sensor output is compared against a spatial template (e.g., a digital mask overlaid on the representation) to determine whether external references in the representation align with corresponding reference indicators in the spatial template. When alignment is required, the removable sensor is aligned by one or both of the following until the external references in a representation of sensor data at an updated current location align with the corresponding reference indicators in the spatial template: (i) adjusting the position of the removable sensor on the vehicle or (ii) adjusting the representation of the sensor output to simulate such repositioning.

Aligning sensors on vehicles using sensor output

A computer-implemented method is provided for detecting a dynamic object in a visual line of sight of an aircraft. The method includes implementing, by a computer system, the following operations: receiving at least two image frames; detecting a horizon within at least one of the at least two image frames; segmenting each of the at least two image frames into at least first and second search regions using the detected horizon, wherein the first search region is defined above the detected horizon in the at least two image frames and the second search region is defined below the horizon in the at least two image frames; determining, across the at least two image frames, a motion vector field within at least one of the first search region or the second search region; and identifying a detection proposal using the determined motion vector field.

Method and system for aerial object detection

A method, apparatus and computer program product are provided to generate a model of one or more objects relative to a vehicle. In the context of a method, radar information is received in the form of in-phase quadrature (IQ) data and the IQ data is converted to one or more first range-doppler maps. The method further includes evaluating the one or more first range-doppler maps with a machine learning model to generate the model that captures the detection of the one or more objects relative to the vehicle. A corresponding apparatus and computer program product are also provided.

Radar-based method and apparatus for generating a model of an object relative to a vehicle

In an example, a method is described. The method includes causing one or more sensors arranged on an aircraft to acquire, over a window of time, first data associated with a first object that is within an environment of the aircraft, where the one or more sensors include one or more of a light detection and ranging (LIDAR) sensor, a radar sensor, or a camera, causing an array of microphones arranged on the aircraft to acquire, over approximately the same window of time as the first data is acquired, first acoustic data associated with the first object, and training a machine learning model by using the first acoustic data as an input value to the machine learning model and by using an azimuth, a range, an elevation, and a type of the first object identified from the first data as ground truth output labels for the machine learning model.

Methods and systems for acoustic machine perception for an aircraft

A computing device, a method and a computer program product are provided to generate realistic synthetic image data that is utilized to train, test and/or deploy a computer vision model, such as to recognize an object from an image, to identify a visual anomaly in the object from an image of the object or the like. In the context of a method, a plurality of computer generated three-dimensional (3D) models of an object are generated. The method also generates realistic synthetic image data representative of each of the plurality of computer generated 3D models. The realistic synthetic image data is generated by utilizing a first machine learning model trained with pairs of computer generated synthetic image data and real image data of the object. The method further trains, tests or deploys the computer vision model to recognize the object from an image based upon the realistic synthetic image data.

Computing device and method for generating realistic synthetic image data

A method including executing a logical computing element (LCE) on a server. Worker LCEs are executed on the server. A first electronic file comprising geometry data in a first data structure is received at the controller LCE. An available worker LCE is identified, by the controller LCE, as an in-use worker LCE from among the worker LCEs. The geometry data is imported by the in-use worker LCE. A job instance is established by the in-use worker LCE. A rendering engine is launched by the in-use worker LCE. The rendering engine generates, for the job instance and using the geometry data, a dataset file in a second data structure different than the first data structure. The dataset file is returned by the in-use worker LCE to the controller LCE. The dataset file is returned by the controller LCE to a remote computer.

Method for automatic creation of real-time rendering content

A method of additively manufacturing an object comprises feeding a feedstock line into a delivery guide. The feedstock line has a length and comprises a continuous flexible line. The continuous flexible line has a peripheral surface. The feedstock line further comprises a covering, releasably coupled to the peripheral surface of the continuous flexible line. The method also comprises removing the covering from the peripheral surface of the continuous flexible line before the continuous flexible line is deposited along a print path and depositing the continuous flexible line along the print path using the delivery guide.

Methods for additive manufacturing

Systems for thermal control of additive manufacturing comprise a build volume within which a part is additively manufactured; a heat source positioned relative to the build volume and configured to actively deliver heat to discrete sections of the part as it is being additively manufactured; and a controller operatively coupled to the heat source and configured to direct delivery of heat from the heat source to discrete sections of the part as it is being additively manufactured to impart desired physical properties to the part. Methods of additively manufacturing a part comprise additively building a part from a feedstock material; and actively heating discrete sections of the part as the part is being additively built to impart desired physical properties to the part.

Systems and methods for thermal control of additive manufacturing

A system for additively manufacturing an object comprises a source of a feedstock line, a rigidizing mechanism that receives the feedstock line from the source and transforms the resin from a first at least partially uncured state to a rigid at least partially uncured state, a delivery guide that deposits the feedstock line along a print path, a feed mechanism that feeds the feedstock line through the delivery guide, a de-rigidizing mechanism that transforms the resin from the rigid at least partially uncured state to a second at least partially uncured state, and a curing mechanism that transforms the resin from the second at least partially uncured state to an at least partially cured state.

Systems and methods for additive manufacturing

A computer-implemented method for generating a training set of images and labels for a native environment includes receiving physical coordinate sets, retrieving environmental model data corresponding to a georeferenced model of the environment, and creating a plurality of two-dimensional (2-D) rendered images each corresponding to a view from one of the physical coordinate sets. The 2-D rendered images include one or more of the environmental features. The method also includes generating linking data associating each of the 2-D rendered images with (i) labels for the one or more included environmental features and (ii) a corresponding native image. Additionally, the method includes storing the training set including the 2-D rendered images, labels, corresponding native images, and linking data.

Systems and methods for automatically generating training image sets for an environment

Systems and methods for additively manufacturing composite parts are disclosed. Methods comprise combining a plurality of pre-consolidated tows to define a macro tow and dispensing the macro tow in three dimensions to define the composite part. Each pre-consolidated tow comprises a fiber tow within a non-liquid binding matrix. The combining comprises actively altering a shape and/or size of a cross-sectional profile of the macro tow along a length of the macro tow as it is being defined.

Systems and methods for additively manufacturing composite parts

Growing community of inventors

Lynnwood, WA, United States of America

Nick Shadbeh Evans