Artificial Intelligence Techniques for Semi-Automated Forces Based on Potential Tactics

Abstract

In this Phase 1 SBIR research we proved the feasibility of a graphical tactics language. We showed through a proof of concept prototype that tactics in this language can be entered in a graphical tactics editor. We also showed that these tactics can be used to implement tactical formations appropriate to arbitrary terrain, and that they can control SAF movement. We researched armor doctrine and tactics from a variety of sources and cultures that are not currently used to control SAF in U.S. Army simulations. We used these tactics to determine which tactic are most naturally expressed and manipulated graphically, and also used them to define the capabilities and expressiveness necessary in a graphical tactics language. We also created a demonstration data base of these tactics using the graphical tactics language and showed that case based reasoning can be used to automatically select tactics appropriate to a given terrain. We used a simulation that responds to a subset of commands available in ModSAF, and provides a subset of the information available in ModSAF to develop a SAF controller.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Oct 03, 1996
Accession Number
ADA365090

Entities

People

  • Drew Downes
  • Richard Stottler
  • Spencer Menlove

Organizations

  • Stottler Henke Associates

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Arabs
  • Artificial Intelligence
  • Books
  • Cold War
  • Computational Complexity
  • Databases
  • Doctrine
  • Instruction Set Architecture
  • Instructions
  • Language
  • Light Armored Vehicles
  • Recognition
  • Simulations
  • Simulators
  • Training
  • Warfare

Readers

  • Database Systems and Applications
  • Military Training and Readiness Simulation

Technology Areas

  • AI & ML
  • AI & ML - Autonomous Systems
  • AI & ML - Information Retrieval