Intelligent Haptic Sensor System for Robotic Manipulation

Abstract—Controlling robotic interventions on small devices creates important challenges on the sensing stage as resolution limitations of noncontact sensors are rapidly reached. The inte-gration of haptic sensors to refine information provided by vision sensors appears as a very promising approach in the development of autonomous robotic systems because it reproduces the multi-plicity of sensing sources used by humans. This paper discusses an intelligent multimodal sensor system developed to enhance the haptic control of robotic manipulations of small three-dimen-sional (3-D) objects. The proposed system combines a 16 16 array of force sensing resistor (FSR) elements to refine 3-D shape measurements in selected areas previously monitored with a laser range finder. Using the integrated technologies, the sensor system is able to recognize small-size objects that cannot be accurately differentiated through range measurements and provides an estimate of the objects orientation. Characteristics of the system are demonstrated in the context of a robotic intervention that requires fine objects to be localized and identified for their shape and orientation. Index Terms—Haptics, laser measurement applications, micro-processors applications, neural networks, object recognition, robot tactile systems. I