Capacitive sensor for object ranging and material type identification

This paper presents a system for object ranging and material type identification using a multifrequency approach for a capacitive sensor. It is shown through an experimental study that the deviation in the readings taken at different sensor drive frequencies and the variation in consecutive readings provide sufficient information to distinguish a range of material types commonly found in a number of environments. A supervised learning scheme is used to classify the material type of planar patches. Extensive experimental evidence is presented to demonstrate the potential of the system. The capacitive based, object penetrating, material type identification is targeted for use with an autonomous robotic system for steel bridge maintenance; significantly different interaction is required for each of the various materials present. Experimental results demonstrate that the information from the sensor is sufficient to range and identify the material type (via physical properties) of an object present in a scene where a bridge structure is being grit-blasted.