The Research And Design Of Evolutionary Behavior For Autonomous Mobile Robot

Evolutionary Robot (ER) is the robot using evolutionary algorithm and has the ability to adapt to dynamic environment. It can solve the above problem well.This paper first introduces the developing history of ER and the research status quo home and abroad, and describes principle and characteristic of several evolutionary algorithms.Then the paper researches into the evolutionary algorithm. The algorithm employed by the paper (genetic algorithm combined by artificial neural network) is presented after expounding the genetic algorithm (GA).Afterwards the paper studies the realization of evolutionary behavior—obstacle avoidance. A three-wheeled mobile robot is designed. The neural controller is discussed in emphasis in the paper. It is realized mainly by MCU and weight values are optimized using genetic algorithm, which is realized on the computer because of the complexity of the algorithm and the data can be transported by serial port. Finally the experiment proves the design can make robot avoid the obstacle freely.The paper discusses the hardware implementation of genetic algorithm. A hardware architecture based on FPGA (Field Programmable Gate Array) is presented, which is capable of population storage, selection, crossover, mutation and fitness evaluation. The design utilizes Xilinx FPGA XC2S200, which shortens processing time and has broad application.Finally the paper discusses several problems related to ER and summarizes the paper.