Realization of Optimum Discrete-Time Nonlinear Estimators,

Abstract

The authors discuss the problems associated with the implementation of optimal discrete-time nonlinear filters on a digital computer. For storage of the conditional densities the authors consider a point mass representation on a peculiar form of floating grid. In order to implement the Bayes-law computation the authors introduced a simplifying ellipsoid tracking technique which eliminates most of the unnecessary points from the computation. The authors also discuss a method for handling multimodal densities and a simple illustrative example. (Author)

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1971
Accession Number
AD0741892

Entities

People

  • Kenneth D. Senne
  • Richard S. Bucy

Organizations

  • University of Southern California

Tags

DTIC Thesaurus Topics

  • Computational Complexity
  • Computations
  • Computers
  • Computing Devices
  • Digital Computers
  • Ellipsoids
  • Estimators
  • Mathematical Analysis
  • Mathematics

Readers

  • Control Systems Engineering.
  • Neural Network Machine Learning.
  • Systems Analysis and Design