The Boeing Company

Huafeng Yu

Tyler Charles Staudinger

Daniel S ReMine

Zachary D Jorgensen

Jan Wei Pan

Daniel S Remine

A method and apparatus for performing automated supervision and inspection of an assembly process. The method is implemented using a computer system. Sensor data is generated at an assembly site using a sensor system positioned relative to the assembly site. A three-dimensional global map for the assembly site and an assembly being built at the assembly site is generated using the sensor data. A current stage of an assembly process for building an assembly at the assembly site is identified using the three-dimensional global map. A context for the current stage is identified. A quality report for the assembly is generated based on the three-dimensional global map and the context for the current stage.

Automated supervision and inspection of assembly process

A method and apparatus for performing automated supervision and inspection of an assembly process. The method is implemented using a computer system. Sensor data is generated at an assembly site using a sensor system positioned relative to the assembly site. A current stage of an assembly process for building an assembly at the assembly site is identified using the sensor data. A context for the current stage is identified. A quality report for the assembly is generated based on the sensor data and the context for the current stage.

A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data can be generated for each distinct image. This and other methods can be used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Generative image synthesis for training deep learning machines

A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Growing community of inventors

Santa Clara, CA, United States of America

Huafeng Yu