Robot navigation using tube skeletons and fast marching

To navigate in complex environments, a robot needs to reach a compromise between the need for having efficient and optimized trajectories and the need for reacting to unexpected events. This paper presents a new sensor based non-holonomic Path Planner which integrates the global motion planning and local obstacle avoidance capabilities. In the first step the safest areas in the environment are extracted by means of a tube skeleton similar to a Voronoi diagram but with tubular shape. In the second step Fast Marching Method is applied to the tube skeleton extracted areas in order to obtain the best path in terms of smoothness and safety. At the same time, during the motion, the algorithm modifies the calculated path when it encounters obstacles or other unforeseen dynamic objects that can not be included in the a priori map. In this way the trajectory obtained is the shortest between the safe possible ones. The method combines map-based and sensor-based planning operations to provide a reliable motion plan, while it operates at the sensor frequency. The main characteristics are speed and reliability, because the map dimensions are reduced to an unidimensional map and this map represents the safest areas in the environment for moving the robot.