Optimal Path Analyzer (Version 1.0)

Abstract

This report describes the function, operation, test and evaluation results of the Optimal Path Analyzer (Version 1.0), a locally connected artificial neural network that maps an optimal path from a given starting point to a given destination through a field of obstacles. A simplified map was drawn and superimposed on a grid field representing a locally connected neural network. Interconnection weights were fixed values based upon the ease or difficulty of movement from one neuron to another. Initially, the output values of all processing elements were set to 1 with two noteworthy exceptions: 1) those located with the mountain, lake, quicksand pit, and RADC building were set to 0 and, 2) the destination was set to 1000.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 01, 1989
Accession Number
ADA217542

Entities

People

  • Scott M. Huse

Organizations

  • Rome Laboratory

Tags

Communities of Interest

  • C4I
  • Counter IED
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Air Force
  • Analyzers
  • Artificial Intelligence
  • Artificial Intelligence Software
  • Classification
  • Color Coding
  • Command And Control
  • Computer Languages
  • Computer Programming
  • Computers
  • Digital Maps
  • Neural Networks
  • Pattern Recognition
  • Security
  • Self Organizing Systems
  • Test And Evaluation
  • Training

Readers

  • Computer Networking
  • Computer Science.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Neural Networks