The Use of Genetic Algorithms for Flight Test and Evaluation of Artificial Intelligence and Complex Software Systems

reportActive / Technical Report | Accession Number: ADA284824 | Open PDF

Abstract:

Artificial Intelligence AI technologies are emerging from research laboratories into industry, particularly into the field of aviation. One such application is the ARPAUSAF Pilots Associate, a set of cooperating expert systems designed to aid the tactical pilot in a combat situation. There are currently no rigorous methods for the test and evaluation of such tactical airborne expert systems. The focus of this program, sponsored in part by the Office of Naval Technology, is the development of a test and evaluation facility for tactical airborne systems which incorporate artificial intelligence. In particular, the subject of this paper is the development of a genetic algorithm GA which will automatically find those test cases for which the system under test performs most poorly

Security Markings

DOCUMENT & CONTEXTUAL SUMMARY

Distribution:
Approved For Public Release

RECORD

Collection: TR
Identifying Numbers
Subject Terms