Neural networks based sensorial signal fusion: an application to material identification

Data acquisition and learning capabilities are necessary for an intelligent system operating in unstructured, dynamically changing environments. For this purpose, a method for the effective use of multiple sensors must be developed. This paper shows how multisensor fusion can be accomplished by neural networks. It first summarizes the conventional fusion techniques and consequently describes the use of neural networks for sensor fusion as well as their advantages. Finally, an application is presented where a neural network is used to fuse the signals of several sensors, of different type, for material identification purposes