On-line path planning for robot manipulators in dynamic environments

Path planning for robot manipulators is a complex subject, which is why most research has been restricted to static environments, where off-line path planning is acceptable, and very little work has been done on dynamic environments. On-line path planning is normally based on local algorithms that end up being inefficient due to their lack of global information (local minima problems). In this paper we present a new method for on-line path planning in dynamic environments. It solves the lack of global vision of local methods by using a hybrid two stage framework that combines global and local planning.