Robot Navigation in an Uncertain Environment using Dynamic programming via Markov decision process

This paper presents the design of a controller to navigate a robot through a clustered and uncertain environment. The approach employed is Dynamic Programming using Markov Decision process. The optimal policy and value function for the given stage cost, that will navigate the robot from its initial point to the destination without colliding with obstacles in its path is determined. The algorithm is implemented in MATLAB and simulation results of optimal policy and value function are obtained.