Genetic-Based Motion Planning for Articulated Robotic Manipulators

摘要

A genetic based algorithm for the minimum time trajectory planning of articulatedrobotic manipulators is proposed. The planning procedure is performed in the configuration space and respects all physical constraints imposed on the manipulator design, including the limits on the torque values applied to the motor of each joint of the arm. The complete nonlinear dynamic robot model is incorporated in the formulation. The purpose of the algorithm is to tessellate joint space into a grid of possible motion nodes, where at each option node, given the position and velocity at the previous node, possible velocity values are constrained by the time optimality together with the dynamics of the arm. The algorithm is proven to be more efficient than conventional heuristic search technique with a reduction of the execution time.