A Sampling-Based Tree Planner for Navigation Among Movable Obstacles

This paper proposes a planner that solves Navigation Among Movable Obstacles problems giving robots the ability to reason about the environment and choose when manipulating obstacles. It finds a path from a robot start configuration S to a goal configuration G taking into consideration the possibility of moving objects if G cannot be reached or if moving objects may significantly shorten the path. The planner combines the A*-Search and the exploration strategy of the Kinodynamic Motion Planning by Interior-Exterior Cell Exploration algorithm. It is locally optimal and independent from the size of the map and from the number, shape, and position of obstacles. It assumes full world knowledge but it can be easily extended in order to explore unknown environments.