Integrating uncertainty and landmarks in path planning for car-like robots

This paper presents the first path planner taking into account both non-holonomic and uncertainty constraints, The case of a car-like robot equipped with a relative localization system and therefore subject to uncertainty on its configuration is considered. Assuming the existence of landmarks allowing the robot to relocalize itself in particular places, me present an algorithm that computes paths that are both feasible and robust. in other words, they respect the non-holonomic constraints of a car-lire robot and the robot is assured to reach its goal by following them no matter what its control and sensing errors are. Copyright (C) 1998 IFAC.