The objective of the Robotic Touch Sensing project is to develop an artificial sensate skin for robots to extend the perceptual capabilities of robotic manipulators to include touch. Under this effort we are developing tactile sensor arrays using piezoresistive sensing elements and have demonstrated a method for determining the location and magnitude of a contact (or contacts) for a multi-touch artificial skin by analyzing the responses from the sensors embedded within the skin. The sensate skin algorithm compresses the feedback from the artificial skin, allowing compliance control algorithms to react to sensed forces resulting from environmental collisions. The sensate skin uses an embedded array of piezoresistive sensors, and an algorithm that can determine the responses of the underlying sensors affected by each contact, to detect and classify contacts. The detection algorithm uses K-means clustering, rules for contact disambiguation, and 3D trigonometric calculations (relating areas under conic sections to force distribution). The sensate skin algorithm achieves graceful degradation in the presence of sensor failures by detecting and selectively ignoring faulty sensors.
Navy Center for Artificial Intelligence
Information Technology Division
Naval Research Laboratory
Washington DC 20375
Email: w5514 "at" itd.nrl.navy.mil