To move in an unknown or uncertain environment, a mobile robot must take observations from many different sensors for providing information to build a representation of the external world. Ultrasonic sensors can provide range data easily; but they are not sufficient for environment recognition due to its large beam opening angle. In this article, the beam-opening angle problem of ultrasonic range sensor is solved by using artificial neural networks to fuse multiple ultrasonic sensors. On the other hand, a mathematical model about the same problem was also derived. Both simulation and experimental results of scanning images are presented. The line extractor of sensor image is developed by using the regression model with a little modification. The simulation results show this method is useful for environment recognition of robotic systems.