Raytheon Company

Steven J Shumadine

Darrell Young

Jonathan Goldstein

Christopher A Eccles

Discussed herein are devices, systems, and methods for decentralized device management. A method can include receiving a first message from a second device, implementing a first machine learning (ML) model that operates on the received first message and an observation to determine a next objective to be completed by the first device, and training a simulator to produce the first message based on the observation.

Decentralized control via adaptive importance encoding

A computer obtains image frames. The computer identifies a chip within the image frames, the chip having a position and dimensions determined based on a lane width. Based on a speed and a length of a vehicle passing through a field of view of the camera, the computer selects a subset of the image frames. The computer takes, from each of the image frames in the subset, the identified chip for use as input to an artificial neural network (ANN). The computer individually provides each taken chip as input to the ANN to generate an ANN output. Based on a combination of the ANN outputs, the computer identifies a shape, a number of axles, and a number of segments of the vehicle. The computer provides a tuple representing the vehicle shape, the number of axles, and the number of segments.

Growing community of inventors

Herndon, VA, United States of America

Steven J Shumadine