Motion Planning with Cartesian Workspace Information

We propose three extensions to the known sampling-based Exploring/Exploiting Tree (EET) Robot Motion Planner with following considerations: a) robot joint motion bounds, b) additional constraints on robot end-effector pose and c) parallelization of planning procedures to get alternative solutions. We also tackle the gap between global and local motion planning by combining sampling-based motion planning and reactive control approaches. These modifications complement the EET algorithm, which enables our planners to be more beneficial for practical applications. The experimental results demonstrate that our extended EET planners outperform other state-of-the-art sampling-based motion planners for some planning problems according to criteria such as planning time and path length. Copyright (C) 2020 The Authors.