OPTIMUM SHORT PATH FINDER FOR ROBOT USING Q-LEARNING

Abstract

ABSTRACT:- Programming robots is a useful tedious task, so there is growinginterest in building robots which can learn by themselves. This paper describes theReinforcement Learning and teaching approach like Queue Learning (Q-Learning) to beimplemented for robotics technology environment navigation and exploration. Q – Learningalgorithm is one of the widely used online learning methods in robotics; it is simple, efficient,and not need to complex process as in adaptive system. The aim of this work is to empowerthe agent to learn a certain goal directed navigation strategy and to generate a shortest path instatic environment which contain static obstacles; it uses one of the important intelligentsearch methods the “heuristic”. It makes a necessary modification for the search algorithm tosuit the way of solving the problem. In our approach of learning from demonstration, therobot learns a reward function from the demonstration and a task model from repeatedattempts (trials) to perform the task. A simplified reinforcement learning algorithm based onone-step Q-Learning that is optimized in speed and memory consumption is proposed andimplemented in Visual Basic language (VB). The robot can be built using stepper motors andany available microcontroller like 89c52 with its driver circuit to utilize of their matching.Keywords: Reinforcement Learning, Q-Learning, Navigation, Robot,microcontroller.