The Community for Technology Leaders
Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence (1997)
Newport Beach, CA
Nov. 3, 1997 to Nov. 8, 1997
ISBN: 0-8186-8203-5
pp: 0278
F.W. Moore , Dept. of Comput. Sci., Dayton Univ., OH, USA
O.N. Garcia , Dept. of Comput. Sci., Dayton Univ., OH, USA
ABSTRACT
Abstract: Traditional analytic or control-theoretic solutions to the problem of optimizing evasive maneuvers in the extended two-dimensional pursuer/evader problem require the evader to execute specific sequences of maneuvers at precise pursuer/evader distances. These solutions depend upon several pursuer-specific characteristics, and fail to effectively account for uncertainty about the state of the pursuer. This paper describes the implementation of a genetic programming system that evolves optimized solutions to the extended two-dimensional pursuer/evader problem that do not depend upon knowledge of the pursuer's current state. Best-of-run programs execute strategies by which an evader may maneuver to successfully evade a pursuer starting from a wide range of relative initial positions, under conditions where the state of the pursuer is unknown or uncertain.
INDEX TERMS
differential games; evasive maneuver optimization; uncertainty; two-dimensional pursuer-evader problem; maneuver sequences; genetic programming system; competitive zero sum game; air defence; differential games
CITATION

F. Moore and O. Garcia, "A new methodology for optimizing evasive maneuvers under uncertainty in the extended two-dimensional pursuer/evader problem," Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence(ICTAI), Newport Beach, CA, 1997, pp. 0278.
doi:10.1109/TAI.1997.632267
93 ms
(Ver 3.3 (11022016))