Design using genetic algorithms of hierarchical hybrid fuzzy-PID controllers of two-link robotic arms

Fuzzy-logic controllers (FLCs) have been shown to be very promising in controlling illmodeled and complicated systems. Moreover, they offer an alternative to more traditional robot control schemes, and this alternative can be more readily integrated with the artificial intelligence required for task planning and decision making, both crucial to robotics. However, the traditional methods of designing FLCs are based on expert heuristic knowledge and trial and error, and are often tedious and unyielding. In this article, we develop a computer-implemented procedure for designing a hierarchical hybrid fuzzy-PID (HHFPID) controller for the position and trajectory control of a two-link robotic arm. This procedure combines genetic algorithms (GAs), expert knowledge, and fuzzy learning from examples. We will discuss the computational issues of our approach, and the design of fitness functions and encoding schemes required by the genetic algorithms. Based on extensive simulation studies, we conclude that the GA-designed controller has a satisfactory and sometimes superior performance.