Genetic-algorithm-based fuzzy control of spacecraft autonomous rendezvous

The combination of the control capabilities of fuzzy logic with the learning capabilities of genetic algorithms is investigated. Fuzzy logic allows for the uncertainty inherent in most control problems to be incorporated into conventional expert systems. Although fuzzy-logic-based expert systems have been used successfully for controlling a number of physical systems, the tasks of selecting acceptable fuzzy membership functions and rule sets have generally been accomplished via subjective decision-making. In this paper, high-performance fuzzy membership functions and efficient rules for a fuzzy logic controller that manipulates a mathematical model simulating the autonomous rendezvous of spacecraft are discovered using a genetic algorithm, a search technique based on the mechanics of natural genetics. The membership functions and rules discovered by the genetic algorithm provide for a more efficient fuzzy logic controller than membership functions selected by the authors for the rendezvous problem. Thus, genetic algorithms are potentially an effective and structured approach for designing fuzzy systems. (C) 1997 Elsevier Science Ltd. All rights reserved.