Sensor-based behavior control for an autonomous underwater vehicle

In this paper, we evaluate a set of core functions that allow an underwater robot to perform surveillance under operator control. Specifically, we are interested in behaviors that facilitate the monitoring of organisms on a coral reef, and we present behaviors and interaction modes for a small underwater robot. In particular, we address some challenging issues arising from the underwater environment: visual processing, interactive communication with an underwater crew and, finally, orientation and motion of the vehicle through a hovering mode. The visual processing consists of target tracking using various techniques (color segmentation, color histogram and mean shift). Communication underwater is achieved through printed cards with robustly identifiable visual markers on them. Finally, the hovering gait developed for this vehicle relies on the planned motion of six flippers to generate the appropriate forces.