Motion Planning with Monte Carlo Random Walks
Weifeng Chen · ERA: Education and Research Archive (University of Alberta) · 2016
This thesis applies the Monte Carlo Random Walk method (MRW) to motion planning. We explore different global and local restart strategies to improve the performance. Several new algorithms based on the MRW approach, such as bidirectional Arvand and optimizing planner Arvand*, are introduced and compared with existing motion planning approaches in the Open Motion Planning Library (OMPL). The results of the experiments show that the Arvand planners are competitive against other motion planners on the planning problems provided by OMPL.