Statistical evaluation of an evolutionary algorithm for minimum time trajectory planning problem for industrial robots [Online]
The International Journal of Advanced Manufacturing Technology
First page 1
Last page 18
This paper presents, evaluates and validates a genetic algorithm procedure with parallel-populations for the obtaining of minimum time trajectories for robot manipulators. The aim of the algorithm is to construct smooth joint trajectories for robot manipulators using cubic polynomial functions, where the sequence of the robot congurations is already given. Three dierent types of constraints are considered in this work: (1) Kinematics: these include the limits of joint velocities, accelerations, and jerk. (2) Dynamic: which include limits of torque, power and energy. (3) Payload constraints. A complete statistical analysis using ANOVA test is introduced in order to evaluate the eciency of the proposed algorithm. In addition, a comparison analysis between the results of the proposed algorithm and other dierent techniques found in the literature is described in the experimental section of this paper.