|
Vol: 56(70) No: 3 / September 2011 JSBSim Applications to UAV Flight Dynamics Models Eusebiu Marcu Chair Elie Carafoli, “Politehnica” University of Bucharest, Faculty of Aerospace Engineering, Str. Gheorghe Polizu, nr. 1, sector 1, 011061, Bucharest, Romania, phone: +40 768 51 64 13, e-mail: marcueusebiu@gmail.com Keywords: genetic algorithms (GA), unmanned aerial vehicle (UAV), flight dynamics model (FDM), swarm intelligence, fuzzy logic Abstract This paper introduces a new approach for controlling unmanned aerial vehicles (UAV) by using genetic algorithms (GA) – a type of intelligent control. The new approach consists in a modified and novel way of evaluating the fitness function based on aircraft state parameters and not based on the values of chromosomes – control parameters. Also, the research is based on a different way of storing information in chromosomes. The genetic information is defined from aircraft's commands control values, values that are the input to flight dynamics model. The state of the aircraft will be defined as the output of the flight dynamics model (FDM). This information is the base of the genetic algorithms model. Also, a hybrid approach will be presented based on swarm intelligence and fuzzy logic. The swarm intelligence technique will be used in order to determine the UAV trajectory given the start and end points (coordinates and heading) and the UAV characteristics. The fuzzy logic technique will be used in order to control the UAV flight commands. The paper is structured as follows: in the beginning the benefits of creating artificial intelligent pilots and the UAV concept are presented and after that, the genetic algorithm and procedure is presented. Then the genetic algorithm model and its results are presented and finally, the conclusions and future work – the hybrid model – are discussed. References [1] G. J. Barlow, Design of Autonomous Navigation Controllers for Unmanned Aerial Vehicles Using Multi-objective Genetic Programming, North Carolina State University. Raleigh, NC, 2004. [2] C.K. Oh, G. Cowart (Tactical Electronic Warfare Division), RIDDER J. (SoSACorp), Autonomous Navigation Control of UAVs Using Genetic Programming, 2004. [3] J. G. Drew, Unmanned Aerial Vehicle End to End Support Considerations, RAND Corporation, 2005. [4] A. Mehrabian, J. Roshanian, C. Lucas, Near-Optimal Tuning of Linear Controllers Based on Genetic Algorithm and Swarm Intelligence: A Flight Control Example, JAST, VOL 4, pp. 1-12, 2007. [5] P. Stewart, D. Gladwin, M. Parr, J. Stewart, A Multiobjective G.A./Fuzzy Logic augmented flight controller for an F16 aircraft. In: IEEE International Conference on Fuzzy Systems FUZZ-IEEE, pp. 1-6, 2007, 23-26 July 2007, Imperial College, London, UK. [6] H. Duan, S. Liua, J. Wua, Novel intelligent water drops optimization approach to single UCAV smooth trajectory planning, Aerospace Science and Technology, Volume 13, Issue 8, pp. 442-449, 2009. [7] B. L. Stevens, F. L. Lewis, Aircraft Control and Simulation, 2nd edition, John Wiley and Sons, Inc, 2003. [8] NASA CR 2497, A Standard Kinematic Model for Flight Simulation at NASA-Ames, Jan. 1975 [9] J. M. Cooke, M. J. Zyda, D. R. Pradtt, R. B. McGhee, NPSNET: Flight Simulation Dynamic Modeling Using Quaternion, Vol. 1, No. 4, pp. 404-420, 1994. [10] http://jsbsim.sourceforge.net. [11] http://jsbsim.sourceforge.net/aeromatic2.htm. [12] http://jsbsimcommander.sourceforge.net/. [13] Z. Michaelewicz, Genetic Algorithms + Data Structures = Evolution Programs, 3rd edition, Springer, 1996. [14] A. Kirillov – AForge .NET – http://www.aforge.com. [15] E. Bonabeau, M. Dorigo, G. Theraulaz, Swarm Intelligence: From Natural to Artificial Systems, Oxford Univesity Press, 1999. [16] J. Kennedy, R. Eberhart, Particle Swarm Optimization, Proceedings of IEEE International Conference on Neural Networks, no. IV. pp. 1942–1948, 1995. [17] M. Dorigo, Optimization, Learning and Natural Algorithms, PhD thesis, Univesitatea Politehnica din Milano, Italia, 1992. [18] H. Shah-Housseini, Optimization with Nature-Inspired Intelligent Water Drops Algorithm, Evolutionary Computation, I-Tech, pp. 572, 2009. |