Performance of local planners with respect to sampling strategies in sampling-based motion planning

Automatically planning the motion of rigid bodies moving in 3D by translation and rotation in the presence of obstacles has long been a research challenge for mathematicians, algorithm designers and roboticists. The field made dramatic progress with the introduction of the probabilistic and sampling-based "roadmap" approach. However, motion planning when narrow passages are present has remained a challenge.;We present experimental results. In particular, our framework has allowed us to find combinations of sampling strategy choice with local planner choice that can solve difficult benchmark motion planning problems.;This thesis presents a framework for experimenting with combinations of sampling strategies and local planners, and for comparing their performance on user defined input problems. Our framework also allows parallel implementations on a variable number of processing cores.