Fractional Order Dynamical Phenomena in a GA

This work addresses the fractional-order dynamics during the evolution of a GA, which generates a robot manipulator trajectory. In order to investigate the phenomena involved in the GA population evolution, the crossover is exposed to excitation perturbations and the corresponding fitness variations are evaluated. The input/output signals are studied revealing a fractional-order dynamic evolution, characteristic of a long-term system memory. 1 The GA Trajectory Planning Scheme This section presents a GA that calculates the trajectory of a two-link manipulator that is required to move between two points. The path is encoded directly, using real codification, as strings in the joint space to be used by the GA as: [∆t, (q11, q21), . . . , (q1j, q2j), . . . , (q1m, q2m)]. The ith joint variable for a robot intermediate jth position is qij, at time j∆t. The fitness function f adopted for evaluating the trajectories is defined as: f = β1fτ + β2 m j=2 2 i=1 ˙q2 ij + β3 m−1 j=2 ...

• Type: Conference
• Year: 2003
• Where: GECCO
• Authors: Eduardo José Solteiro Pires, José António Tenreiro Machado, Paulo B. de Moura Oliveira
• Keywords: Fractional-order Dynamics, GA Population Evolution, GECCO 2003, Robot Manipulator Trajectory