HELICOPTER FLIGHT CONTROL WITH FUZZY-LOGIC AND GENETIC ALGORITHMS

Researchers at the U.S. Bureau of Mines, in conjunction with researche rs at the University of Alabama and the U.S. Army, have developed a fu zzy system for controlling the flight of UH-I helicopters through vari ous maneuvers. Since flying a helicopter is an extremely difficult tas k, the fuzzy logic controller was necessarily quite complex. In fact, the control tasks were distributed over four individual control units, each of which had its own rules and associated membership functions. Because the fuzzy logic controller was large, and because the rules im plemented in the individual control units were not necessarily those a human pilot would use, an efficient technique for writing the rules w as required. A genetic algorithm was used to discover rules that provi ded for effective control of the helicopter. Genetic algorithms are se arch algorithms based on the mechanics of natural generics, and have d emonstrated the ability to locate rules for fuzzy logic controllers. T his paper describes the architecture of the helicopter fuzzy logic con troller, provides the details of the genetic algorithm application, an d presents the results of an actual flight test using the computer sof tware. Copyright (C) 1996 Elsevier Science Ltd