Diverse Workspace Path Planning for Robot Manipulators

Abstract

We present a novel algorithm that generates a set of diverse workspace paths for
\nmanipulators. By considering more than one possible path we give our manipulator
\nthe flexibility to choose from many possible ways to execute a task. This is
\nparticularly important in cases in which the best workspace path cannot be executed
\nby the manipulator (e.g. due to the presence of obstacles that collide with
\nthe manipulator links). Our workspace paths are generated such that a distance
\nmetric between them is maximized, allowing them to span different workspace regions.
\nManipulator planners mostly focus on solving the problem by analyzing the
\nconfiguration space (e.g. Jacobian-based methods); our approach focuses on analyzing
\nalternative workspace paths which are comparable to the optimal solution in
\nterms of length. This paper introduces our intuitive algorithm and also presents the
\nresults of a series of experiments performed with a simulated 7 DOF robotic arm.