Trajectory optimization using learning from demonstration with meta-heuristic grey wolf algorithm

<span>Nowadays, most robotic systems perform their tasks in an environment that is generally known. Thus, robot's trajectory can be planned advance depending on a given task. However, as part of modern manufacturing which are faced with the requirements to produce high product variety, mobile robots should flexible adapt changing and diverse environments needs. In such scenarios, modification task or change environment, forces operator modify trajectory. Such usually expensive time-consuming, experienced engineers must involved program movements. The current paper presents solution this problem by simplifying process teaching robot new proposed method generates based initial raw demonstration its shape. generated way errors between actual target end positions orientations minimized. To minimize those errors, grey wolf optimization (GWO) algorithm applied. approach demonstrated for two-wheeled robot. Simulation experimental results confirm accuracy trajectories.</span>