In this paper, a genetic algorithm (GA) is used to design faulttolerant analog controllers for a piezoelectric micro-robot. Firstorder and second-order functions are developed to model the robot's piezoelectric actuators, and the GA is used to evolve closed-loop controllers for both models. The GA is first used to assist in traditional PID design and is later used to synthesize variable topology analog controllers. Through the use of a compact circuit representation, runtimes are minimized and controllers are synthesized with minimum population sizes and components. Fault-tolerance is built into the fitness function to facilitate the design of controllers robust to both actuator failure and component failure. The GA is successfully used to design synthetic controllers and to optimize a traditional PID design. This research shows the advantages of GA assisted design when applied to robot-control problems.

The design of an Evolvable Machine VHDL Core is presented, representing a discrete-time processing structure capable of supporting control system applications. This VHDL Core is implemented in an FPGA and is interfaced with an evolutionary algorithm implemented in firmware on a Digital Signal Processor (DSP) to create an evolvable system platform. The salient features of this architecture are presented. The capability to implement IIR filter structures is presented along with the results of the intrinsic evolution of a Jilter. The robustness of the evolved filter design is tested and its unique characteristics are described.

No abstract

No abstract

No abstract