Abstract:
The raw sensory input available to a mobile robot suffers from a variety of shortcomings. Sensor fusion can yield a percept more veridical than is available from any single sensor input. In this project, the fuzzy ARTMAP neural network is used to fuse sonar and visual sonar on a B14 mobile robot. The neural network learns to associate specific sensory inputs with a corresponding distance metric. Once trained, the network yields predictions of range to obstacles that are more accurate than those provided by either sensor type alone. This improvement in accuracy holds across all distances and angles of approach tested.
