X Development LLC

Gearoid Murphy

Diosdado Rey Banatao

Artem Goncharuk

Lance Co Ting Keh

Sujit Sanjeev

Patrick Christopher Leger

Allen Richard Zhao

Neil David Treat

Shruti Badhwar

Alexander Holiday

Anarbek Iskaliyev

A method for generating spectroscopic data includes inputting, by a computing device, a text string comprising a structural representation of a material to an encoder of a natural language processing (NLP) model implemented with a deep neural network. The method includes generating, using the encoder of the NLP model, an encoded representation of the text string. The text string may include latent chemical bond information of the material. The method includes mapping, by the computing device, the encoded representation including the latent chemical bond information to a spectrum array, the spectrum array including predicted spectroscopic data of the material. The method also includes outputting, by the computing device, the spectrum array.

Techniques for predicting the spectra of materials using molecular metadata

Methods and systems for using multiple hyperspectral cameras sensitive to different wavelengths to predict characteristics of objects for further processing, including recycling, are described. The multiple hyperspectral images can be used to predict higher resolution spectra by using a trained machine learning model. The higher resolution spectra may be more easily analyzed to sort plastics into a recyclability category. The hyperspectral images may also be used to identify and analyze dark or black plastics, which are challenging for SWIR, MWIR, and other wavelengths. The machine learning model may also predict the base polymers and contaminants of plastic objects for recycling. The hyperspectral images may be used to predict recyclability and other characteristics using a trained machine learning model.

Sensor fusion approach for plastics identification

Methods, systems, and apparatus for training a machine-learned model using satellite imagery and physical river gauge data as ground-truth information. Methods include receiving, from a user in a graphical user interface presented on a user device, a depth request for depth information at a geolocation. At least two satellite images are received, including the geolocation where a difference in respective capture times of each of the satellite images is within a threshold. The satellite images for the geolocation are provided to a machine-learned river gauge model. The machine-learned river gauge model determines depth information for the geolocation utilizing the satellite images, and provides, to the user in the graphical user interface, the depth information at the geolocation.

Enhanced river gauge

Techniques for selecting a spectroscopic light source include obtaining a light source dataset and a spectroscopic dataset, initializing a genetic algorithm, selecting a first individual solution and a second individual solution from an initial generation of solutions, generating a new individual solution from the first and second individual solutions by combining their respective chromosome encodings, evaluating a specificity of the new individual solution to a target material, adding the new individual solution to a new generation of solutions, populating the new generation of solutions with a plurality of additional individual solutions, generating one or more descendent generations of solutions by iterating the genetic algorithm, selecting one or more implementation individual solutions exhibiting a threshold specificity to the target material, and outputting the one or more implementation individual solutions.

Techniques for selection of light source configurations for material characterization

The present disclosure relates to techniques for deformulating the spectra of arbitrary compound formulations such as polymer formulations into their chemical components. Particularly, aspects of the present disclosure are directed to obtaining an initial set of spectra for a plurality of samples comprising pure samples and composite samples, constructing a basis set of spectra for a plurality of pure samples based on the initial set of spectra, and providing or outputting the basis set of spectrum. The basis set of spectra is constructed in an iterative process that attempts to decompose, using a decomposition algorithm or model, the spectrum from the initial set of spectra in order to differentiate the pure samples from the composite samples. The basis set of spectra may then be used to deduce the composition of a material from a spectrogram.

Deformulation techniques for deducing the composition of a material from a spectrogram

A method includes receiving, by a control system of a robotic device, data about an object in an environment from a remote computing device, where the data comprises at least location data and identifier data. The method further includes, based on the location data, causing at least one appendage of the robotic device to move through a predetermined learning motion path. The method additionally includes, while the at least one appendage moves through the predetermined learning motion path, causing one or more visual sensors to capture a plurality of images for potential association with the identifier data. The method further includes sending, to the remote computing device, the plurality of captured images to be displayed on a display interface of the remote computing device.

Growing community of inventors

Mountain View, CA, United States of America

Gearoid Murphy