Title :
Augmentation of an extended Kalman filter with a neural network
Author :
Fisher, William A. ; Rauch, Herbert E.
Author_Institution :
Lockheed Palo Alto Res. Lab., CA, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
This paper shows how a neural network can augment a Kalman filter by estimating initial conditions and unknown system parameters. The neural network training is done off-line, using an approach similar to multiple Kalman filters. After off-line training, real-time operation can take place using the neural network without the computational requirements of multiple Kalman filters. An example shows how the general regression neural network (GRNN) augments a Kalman filter for terminal guidance of an interceptor missile
Keywords :
Kalman filters; filtering theory; missile guidance; neural nets; extended Kalman filter augmentation; general regression neural network; interceptor missile terminal guidance; neural network; off-line training; Acceleration; Logic; Missiles; Navigation; Neural networks; Preforms; Radar tracking; State estimation; Training data; Vehicles;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374352
