|18-20 April 2001
Lake Como (Milan), Italy
Two-Sided, Genetics-Based Learning To Discover Novel Fighter Combat Maneuvers
R. E. Smith, B. A. Dike, B. Ravichandran, A. El-Fallah, R. K. Mehra
This paper reports the authors' ongoing experience with a system for discovering novel fighter combat maneuvers, using a genetics-based machine learning process, and combat simulation. In effect, the genetic learning system in this application is taking the place of a test pilot, in discovering complex maneuvers from experience. The goal of this work is distinct from that of many other studies, in that innovation, and discovery of novelty (as opposed to optimality), is in itself valuable. This makes the details of aims and techniques somewhat distinct from other genetics-based machine learning research. This paper presents previously unpublished results that show two co-adapting players in similar aircraft. The complexities of analyzing these results, given the red queen effect are discussed. Finally, general implications of this work are discussed.
Generation of time-delay algorithms for anti-air missiles using genetic programming
H. O. Nyongesa
This paper describes the application of genetic programming to generate algorithms for control of time-delays in anti-air missiles equipped with proximity fuzes. Conventional algorithms for determining these delay-times rely on human effort and experience, and are generally deficient. It is demonstrated that by applying genetic programming determination of the timing can be automated and made near-optimal.
Genetic Programming, Evolutionary Algorithms, Time-Delay, Missile Technology, Aerospace, Aircraft
Surface Movement Radar Image Correlation Using Genetic Algorithm
The goal of this work is to describe an application of Genetic Algorithms to to a real aeronautical problem involving radar images. The paper presents the aeronautical problem, the specific implementation of the Genetic Algorithm and the result of the variation of some of the parameters of the Genetic Algorithm in term of time employed by the process, and ability to reach a useful solution of the aeronautical problem in a given time. The aeronautical problem is to find the position, orientation and dimension of a radar observed target. All the methods used here involve the correlation between an actual radar image and a template image. The Genetic Algorithm itself is not standard since it involve a dynamic computation of the best value for the probability of mutation. The probability of mutation (Pm) is dynamically adjusted according to the fitness of the best individual so that a worse fitness gives a greater probability of mutation and a better individual gives a lower probability of mutation.
Radar, Image Correlation, Genetic Algorithms, A-SMGCS, Air Traffic Control
A Conceptual Approach for Simultaneous Flight Schedule Construction with Genetic Algorithms
Tobias Grosche, Armin Heinzl, Franz Rothlauf
In this paper, a new conceptual approach for flight schedule construction will be developed. Until now, the construction of a flight schedule is performed by decomposing the overall problem into subproblems and by solving these subproblems with various optimization techniques. The new approach constructs flight schedules with the help of genetic algorithms. Each individual of a population represents a complete flight schedule. This encoding avoids the artificial decomposition of the planning problem. With the help of genetic operators, flight schedule construction may be conducted simultaneously, efficiently searching for better solutions.
|Web site designed and maintained by Chris Osborne at EvoNet.|