Model-based object recognition using a large-field passive tactile sensor

The results of a model-driven touch sensor recognition experiment are reported. The touch sensor used is a large-field tactile array. Object features appropriate for touch sensor recognition are extracted from a geometric model of an object, and a dual spherical image is formed. Both geometric and dynamic features are used to identify objects and their position and orientation on the touch sensor. Experiments show that geometric features extracted from the model are effective but that dynamic features must be determined empirically. Correct object identification rates, even for very similar objects, exceed 90%, a success rate much higher than would have been expected from only two-dimensional contact patterns. The position and orientation of objects, once identified, are very reliable. The authors conclude that large-field tactile sensors could prove useful in the automatic palletizing problem when object models (from a computer-aided design system, for example) can be utilized