Autonomous SLAM-based Robotic Wheelchair's Assistive Navigation for Confined Spaces

in this work, an interface specially designed for a robotic wheelchair's navigation within confined spaces is presented. The interface performance is based on two modus: autonomous and non-autonomous. The non-autonomous execution of the robotic wheelchair interface is performed by means of a joystick. The joystick is adapted to the wheelchair's patient capabilities and it governs the motion of the vehicle within the environment. The autonomous modus of the robotic wheelchair is executed when the user has to turn a given angle within the environment. The turning strategy is performed by means of both: a maneuverability algorithm which is compatible with the wheelchair's kinematics and the SLAM (Simultaneous Localization and Mapping) algorithm. In addition, the autonomous modus is composed by two modules: a path planning module and a control module. The path planning module uses the map information provided by the SLAM algorithm to generate a safe path compatible with the robotic wheelchair. Such path will allow the vehicle to reach the orientation -angle of turning- given by the user. The control module governs the motion of the robotic wheelchair by means of a trajectory controller when following the path generated by the path planning algorithm. The controller references are updated by the SLAM estimation of the wheelchair's pose within the environment. Experimental results using a real robotic wheelchair are also shown in this work. Copyright (C) 2011 CEA.