Information Systems Laboratories, Inc.

Other

Jameson Bergin

Joseph R Guerci

J Doss Halsey

David R Kirk

John Don Carlos

Brian Watson

Paul Matthew Techau

Jeffrey Richard Ridgway

Sandeep Gogineni

Gavin McGee

Joel R Studer

Colton Smith

Raymond M Guerci

A novel system and method are described that allows for implementation of compact and efficient deep learning AI solutions to advanced sensor signal processing functions. The process includes the following stages: (1) A method for generating requisite annotated training data in sufficient quantity to ensure convergence of a deep learning neural network (DNN); (2) A method for implementing the resulting DNN onto a Spiking Neural Network (SNN) architecture amenable to efficient neuromorphic integrated circuit (IC) architectures; (3) A method for implementing the solution onto a neuromorphic IC; and (4) A statistical method for ensuring reliable performance.

Process and method for real-time sensor neuromorphic processing

The present invention is for a system and method for testing an RF/radar system in a simulated open-air environment. During a test, the RF/radar system-under-test interfaces directly with the simulated open-air environment and operates in real time. For test purposes, an environmental database is provided to mimic the simulated open-air environment using a plurality of digitized impulse functions. A computation engine then cross-correlates the digitized impulse functions of the environmental database in fast time with digitized RF transmissions from the system-under-test to format a digital convolution. The digital convolution is then test-evaluated. For the present invention, the digital convolution is based on the theory of Green's Functions and is influenced by propagation and reflection physics (i.e. Maxwell's Equations) that are pertinent to the simulated open-air environment.

System and method for modeling environmental data

A simulator is provided for dynamically testing and evaluating an electromagnetic radiation in real-time. The performance of radiation from a system-under-test is evaluated as it interacts with a moving target in an ever-changing simulated environment. The simulator includes a computer for synchronized control of a PNT database and of an environmental database. In detail, the PNT database contains Position, Navigation and Timing (PNT) information of the target, and the environmental database contains information pertaining to meteorological conditions and topographical characteristics in the simulated environment. In combination, the computer evaluates a synchronized interaction of the electromagnetic radiation with the PNT information from the PNT database, under conditions set by the environmental database. A response record for evaluating a performance of the system-under-test is thereby created.

Real-time electromagnetic environmental simulator

A system for visually tracking the trajectory of an in-flight golf ball through an x-y-z space above a driving range includes a plurality of cameras for respectively creating a video stream of the x-y-z space. Each video stream is presented on a dedicated camera focal plane with information on respective azimuth angles &#x3b8; and elevation angles &#x3d5; from the particular camera to the in-flight golf ball. A central computer is connected with the camera focal plane of each camera to identify a start point for the golf ball, to track its trajectory in the x-y-z space, and to filter out background clutter. A visual display is provided to show the in-flight golf ball from its start point to a target point in real time.

System and method for 3D optical tracking of multiple in-flight golf balls

A radar antenna system includes a single transmitter for creating pulses from a wideband waveform. A splitter divides each pulse into half-power pulses, and sends them along respective paths. On one path, successive half-power pulses are alternately modulated with a phase shift &#x3d5;or &#x3d5;. On the other path, the half-power pulses are not modulated. Each modulated half-power pulse is then combined with an un-modulated half-power pulse to transmit pulses of a full aperture beam with either &#x3d5;or &#x3d5;. This establishes two degrees of freedom for the system. Two separate receivers then simultaneously receive the pulse echoes and a signal processor uses the consequent four degrees of freedom to create a radar indicator with mitigated clutter and useable azimuth estimation. A coherent processing interval can then be selected for multi-mode operation of the system.

Two-channel array for moving target indications

A passive navigation system for an airborne platform includes an on-board computer having a database that contains preprogrammed information regarding pre-existing ground-based signal emitters (e.g. cell-phone, television and radio broadcast transmitters). For each emitter, the database includes the geolocation of the emitter and identifying signal characteristic(s) of each emitter's signal such as frequency, bandwidth and strength. An antenna array and digital receiver cooperate with the computer on the platform to passively receive signals from the emitters and determine a direction of arrival (DOA) for selected signals. The computer also extracts identifying signal characteristic(s) from selected received signals and matches them against the database information to ascertain the geolocation of the emitter that corresponds to the received signal. The platform location is then calculated from the DOA(s) and emitter geolocations using a triangulation-type algorithm. Also, preprogrammed site-specific terrain scattering information can be compared to observed scattered signals to enhance system accuracy.

Intelligent passive navigation system for back-up and verification of GPS

A system and method for detecting a target object through foliage includes a transmitter for generating a low-frequency electromagnetic signal. The signal is directed toward a potential target object for reflection from the potential target object. The system further includes a plurality of mutually dispersed sensors for receiving the reflected signal from the target object. A mechanism is provided to determine the relative locations of the sensors. Signal information from the received signals is sent to a central processor. The central processor inputs the signal information into a beamformer algorithm such as the Maximum Likelihood Method (MLM) to reduce sidelobe ambiguities and resolve the true location of the target from the signal information.

Detecting system having a coherent sparse aperture

A system and method for identifying the position of an airborne platform on a flight path includes at least three radar transceivers that are directed along respective beam paths to generate return signals. Each of the return signals respectively indicate a speed and a direction of the platform relative to points on the surface of the earth. A computer uses the return signal to establish a ground speed, an altitude and a direction of flight for the platform. This information is then used to identify the position of the platform on its flight path. Additionally, the system can include a last known position, or a site-specific radar clutter model, to establish a start point for the platform. The computer can then calculate the position of the platform relative to the start point.

Growing community of inventors

Glastonbury, CT, United States of America

Jameson Bergin