In the present work, a robotic wheelchair navigation system which is specially designed for confined spaces is proposed. In confined spaces, the movements of wheelchairs are restricted by the environment more than other unicycle type vehicles. For example, if the wheelchair is too close to a wall, it can not rotate freely because the front or back may collide with the wall. The navigation system is composed by a path planning module and a control module; both use the environment and robot information provided by a SLAM algorithm to attain their objectives. The planning strategy uses the Monte Carlo technique to find a minimum path within the confined environment and takes into account the variance propagation in the predicted path for ensuring the safe driving of the robot. The objective of the navigation system is to drive the robotic wheelchair within the confined environment in order to reach a desired orientation or posture. © 2010 IEEE.