A NEURAL NETWORK KALMAN FILTER FOR MULTI-SENSOR BASED ROBOTIC CONTROL

Award Information
Agency:
Department of Defense
Branch
Army
Amount:
$300,000.00
Award Year:
1992
Program:
SBIR
Phase:
Phase II
Contract:
n/a
Agency Tracking Number:
8829
Solicitation Year:
n/a
Solicitation Topic Code:
n/a
Solicitation Number:
n/a
Small Business Information
Martingale Research Corp.
100 Allentown Pkwy - Ste 211, Allen, TX, 75002
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
n/a
Principal Investigator:
DR ROBERT L DAWES
(214) 422-4570
Business Contact:
() -
Research Institution:
n/a
Abstract
THE PROPOSED RESEARCH BUILDS UPON THE CONTRACTOR'S PROPRIETARY NEURAL NETWORK SPACE-TIME MEMORY, THE PARAMETRIC AVALANCHE, TO DETERMINE A SET OF DESIGN CHARACTERISTICS FOR NEUROCOMPUTING ARCHITECTURES THAT WILL EFFECTIVELY SUPPORT REAL TIME ACQUISITION AND TRACKING OF MULTIPLE TARGETS USING MULTIPLE SENSORS, AND DEPLOY AND CONTROL MULTIPLE SIMULTANEOUS RESPONSES. THE APPROACH TO THIS PROBLEM IS TO USE THE PARAMETRIC AVALANCHE TO IMPLEMENT A KALMAN FILTER WHICH IS CAPABLE OF TRACKING AND PREDICTING THE EVOLUTION OF LARGE NUMBERS OF OBSERVABLE OBJECTS WITH WIDELY DIFFERING DYNAMICS, AND IS ALSO CAPABLE OF LEARNING TO PREDICT AND (GIVEN ACCESS TO EFFECTORS) TO CONTROL NOVEL SPACE-TIME PATTERNS.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government