Application of new genetic strategy to dynamic control of a mobile robot

Abstract

A new genetic strategy, called a 'genetic algorithm with symmetric code', and its application to robot dynamic optimal control are introduced. This strategy is developed from symmetric code theory. According to the property of a mobile robot's dynamic model, symmetric codes are introduced into the genetic strategy. Two theorems are presented which offer sufficient and necessary conditions for satisfying the final conditions of linear and angular velocities. The problem of trajectory planning of the robot with the existence of obstacles is expressed in the form of an optimal control problem with constraints. The minimum energy used by the robot is taken as the criterion. Included are comparisons of different crossover and encoding techniques. In the four phases of simulation, the new genetic strategy shows itself to be efficient and capable for the trajectory planning of mobile robots and to be more powerful than classical genetic techniques.