An evolutionary approach for time optimal trajectory planning of a roboticmanipulator

We present an application of efficient evolutionary algorithm on the time o ptimal trajectory planning of a manipulator. The proposed method is simple, flexible and provides a near optimal solution among the huge trajectory sp ace. We first outline the differences in the trajectory parameterization me thod between the evolutionary algorithm and the conventional nonlinear prog ramming based approach. Then, we propose two novel evolutionary schemes and investigate their characteristics. The first scheme is based upon the cano nical genetic algorithm (GA) and the penalty function method to tackle the torque constraints, The second scheme, which is basically based on evolutio nary strategy (ES), incorporates effective heuristics to further speed up t he search and utilizes the time scaling method to deal with the constraints on actuator torques. The effectiveness and validity of the proposed method are demonstrated through the simulation study in comparison with other con ventional nonlinear programming based methods. (C) 1999 Elsevier Science In c. All rights reserved.