AI Techniques for Context-Sensitive Tactical Decision Aids

Period of Performance: 12/21/1998 - 06/30/1999

$70K

Phase 1 SBIR

Recipient Firm

Stottler Henke Associates
1650 South Amphlett Boulevard, Suite 300
San Mateo, CA 94402
Principal Investigator

Research Topics

Abstract

In Phase I, SHAI, in cooperation with our consultant, Dr. David Swanson of the Advanced Research Laboratory at Pennsylvania State University, will investigate, design, and implement a prototype of a context-sensitive tactical decision aid system for enhancing the deployment and employment of intelligent acoustic sensors. This system will use knowledge about local environmental conditions and terrain to dynamically determine sensor coverage of the battlefield and make recommendations for optimal sensor emplacement. It will combine knowledge of mission objectives with general tactical knowledge to interpret sensor reports in the context of the current combat situation, assessing from moment to moment which information would be most relevant and important for the user to see. It will also merge reports from multiple sensors, combining them with terrain and tactical data to provide a single coherent picture of the battlefield with maximum accuracy and utility. Since these are complex and difficult problems, we will take an integrated approach using a variety of paradigms, including Case-Based Reasoning, Model-Based Reasoning, Constraint Satisfaction, Bayesian Networks, and Knowledge-Based Representations; techniques we have used with much success in previous projects. BENEFITS: Context-sensitive tactical decision aids are applicable in any situation where intelligent acoustic sensors are employed. This includes a wide array of non-military surveillance applications such as intrusion detection in warehouse complexes, patrol of international borders, and monitoring of animal/livestock activity in wildlife preserves or commercial ranches.