OPTIMAL ROBOT TRAJECTORY PLANNING USING EVOLUTIONARY ALGORITHMS

Abstract

In the last decade, much research has been proposed concerning trajectory generation for manipulators. Also, evolutionary algorithms have been applied in a plethora of fields such as control, robotics, image processing, pattern recognition and speech recognition. In this thesis, we present an optimal trajectory planning approach using evolutionary methods for an industrial manipulator system. Minimum energy consumption is used as a criterion for trajectory generation, and is achieved using genetic algorithms as an optimization tool. We propose the use of cubic spline curves to generate the trajectory between the intermediate points of the path. The problem of kinematics is solved for two-degree-of-freedom linear industrial manipulators. The Newton-Euler technique is used for the formulation of the dynamic equations of the manipulator. The effectiveness of the proposed method is verified through MATLAB simulations.