On manipulation planning

An emerging paradigm in solving the classical motion planning problem (among static obstacles) is to capture the connectivity of the configuration space using a finite (but possibly large) set of landmarks (or nodes) in it. In this paper, the authors extend this paradigm to manipulation planning problem, where the goal is to plan the motion of a robot so that it can move a given object from an initial configuration to a final configuration while avoiding collisions with the static obstacles in the environment. The authors´ specific approach adapts Adraine´s Clew Algorithm that has been shown effective for classical motion planning problem. In the authors´ approach, landmarks are placed in lower dimensional submanifolds of the composite configuration space. These landmarks represent stable grasps that are reachable from the initial configuration. From each new landmark, the planner attempts to reach the goal configuration by executing a local planner, again in a lower (but different) dimensional submanifold of the composite configuration space. The authors have implemented this approach and present initial experiments with a simple 2-DOF planar arm among polygonal obstacles