Model-based stereo-tracking of non-polyhedral objects for automatic disassembly experiments

Automatic disassembly tasks in the engine compartment of a used car constit ute a challenge for control of a disassembly robot by machine vision. Exper ience in exploratory experiments under such conditions forced us to abandon data-driven aggregation of edge elements into straight-line data segments in favor of a direct association of individual edge elements with model seg ments obtained from scene domain models of tools and workpieces. In additio n, we had to switch from a conventional single camera hand-eye configuratio n to a movable stereoconfiguration mounted on a separate 'observer' robot. A eneralisation of our model-based tracking includes the parameters, which characterize the relative pose of one camera with respect to the other one of the stereo-camera set-up, into the set of parameters to be re-estimated for each new stereo image pair. This results in a continuous re-calibration during a relative movement between stereo-camera set-up and tracked object s. Our approach had to be extended further in order to cope with non-polyhe dral objects. The methodological improvements of machine vision in the course of this res earch are treated in detail. We discuss, moreover, the systematic trading-o ff of computational resources for increased robustness which is vital for v isual control of automatic disassembly robots.