Berkshire Grey Operating Company, Inc.

The Charles Stark Draper Laboratory, Inc.

Abraham Schneider

Christopher Geyer

Thomas Wagner

Thomas Koletschka

Matthew T Mason

Joseph M Romano

Benjamin Cohen

Kyle Maroney

John Richard Amend, Jr

William Chu-Hyon McMahan

Lakshman Kumar

Shervin Javdani

John M Irvine

Laura Jane Mariano

William Chu-Hyon Mcmahan

Lev E Givon

Jr Amend John Richard

Joseph Romano

A system for object processing is disclosed. The system includes a framework of processes that enable reliable deployment of artificial intelligence-based policies in a warehouse setting to improve the speed, reliability, and accuracy of the system. The system harnesses a vast number of picks to provide data points to machine learning techniques. These machine learning techniques use the data to refine or reinforce in-use policies to optimize the speed and successful transfer of objects within the system. For example, objects in the system are identified at a supply location, a predetermined set of information regarding object is retrieved and combined with a set of object information and processing parameters determined by the system. The combined information is then used to determine routing of the object according to an initial policy. This policy is then observed, altered, tested, and re-implemented in an altered form.

Systems and methods for learning to extrapolate optimal object routing and handling parameters

A processing system for processing objects is disclosed that includes a plurality of receiving stations for receiving a plurality of objects, each object being associated with prerecorded data, and a plurality of processing stations, each of which is in communication with at least one processing station. Each processing station includes perception means for perceiving data regarding an identity of any of an object or a bin of objects, and capture means for capturing characteristic data regarding an object to provide captured data. Each processing station further includes comparison means for comparing the captured data with the prerecorded data to provide comparison data, and a plurality of distribution stations, each of which is in communication with at least one processing station for receiving objects from the at least one processing station responsive to the comparison data.

Systems and methods for dynamic processing of objects with data verification

A method of predicting progression of a cognitive state in a subject is disclosed including obtaining a neuroimage of the subject, acquiring a data sample from the neuroimage, selecting a time at which to predict progression of the cognitive state, and performing a calculation on the data sample by a transformation function to determine data associated with multiple cognitive metrics. A method of evaluating a cognitive state of a subject is also disclosed including providing a convolutional neural network, training the convolutional neural network with reference data to construct a transformation function, using the transformation function to predict multiple cognitive metrics from a subject data sample and a selected time, and determining the cognitive state of the subject from the predicted cognitive metrics. A cognitive evaluation system is also disclosed including a memory, a processor, and a cognitive state prediction component configured to program the processor with a transformation function.

Deep learning architecture for cognitive examination subscore trajectory prediction in Alzheimer's disease

Growing community of inventors

Andover, MA, United States of America

Abraham Schneider