Genetic Algorithms for Auto-tuning Mobile Robot Motion Control

Abstract

This paper discusses a genetic algorithm (GA) based method for automatically tuning mobile robot motion controllers. The genetic algorithm evolves a controller that is optimised for a given performance measure. Genetic algorithms require a mapping from the genetic code to an implementation. This translation between the chromosome and the implementation allows the use of standard GA libraries, however the assumption constrains the types of problems that can be solved. 1.