On Using a Tactile Sensor for Real-Time Feature Extraction

Object recognition through the use of input from multiple sensors is an important aspect of an autonomous manipulation system. Useful sensors include video cameras, tactile arrays, force gauges and proximity sensors. In this report, we focus on tactile sensors. In tactile object recognition, it is necessary to determine the location and orientation of object edges and surfaces. We propose controllers that utilize a tactile sensor in the feedback loop to track along edges and surfaces. In our control system, the data from the tactile sensor is first processed to find edges. Then a new Hough Transform algorithm is applied to the edge points to determine the line parameters of the detected edges. From these parameters, a control signal to a hybrid controller is generated. In this report, we present the theory for edge detection, the Modified Adaptive Hough Transform, and edge and surface tracking controller design. In addition, simulation and experimental verification of the edge tracking controller are presented. Table of