Automated sensor planning for robotic vision tasks (original) (raw)

In this paper, we present a method to determine viewpoints for a robotic vision system for which object features of interest will simultaneously be visible, inside the field-of-view, in-focus and magnified as required. As part of our previous work, we had analytically characterized the domain of admissible camera locations, orientations and optical settings for which each of the above feature detectability requirements is satisfied separately. In this paper, we present a technique that poses the problem in an optimization setting in order to determine viewpoints that satisfy all requirements simultaneously and with a margin. The formulation and results of the optimization are shown, as well as, experimental results in which a robot vision system is positioned and its lens is set according to this method. Camera views are taken from the computed viewpoints in order to verify that all feature detectability requirements are indeed satisfied.