A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Advanced Technologies

Thesis (M.Eng.) - Asian Institute of Technology, 1998

The purpose of this study is to reduce the training time of the mobile robot control algorithm and to realize the sensors system. This study approaches learning and training process of mobile robot control algorithm, which are improved in every basis. And because multi-task application in the industry, hospital, department store was given as the service by learning robot, developing of decision of mobile robot is quickly growth in the present. The rapidly expanding technological growth support us to know new information and new ideas, which are the power of creative thinking for new control algorithm. New algorithm is developed on reduced learning time and various working ability under varying factor conditions which are concerned. The study found out that profitability of compared memory selecting process has help to improve the robot learning process, which is very important part of robot process operation. Other parts like sensing system, turning system and safety system are important part for robot operation. Motor driver, interface system and outside shape have very little effect on the mobile robot. The result obtained from this developing was new algorithm with learning ability in order to prove the number of learning times and various tasks apply.