A neural network approach for the control of a tracking behavior

The problem of correctly evaluating noisy and incorrect data for the interpretation of ultrasonic sensor signals is an often encountered one. Neural networks, with their inherent characteristics of adaptivity and high fault- and noise-tolerance are well suited for such tasks. In this paper two neural network approaches are described for the control of the tracking behavior of an autonomous mobile robot. Input data are provided by a set of ultrasonic sensors mounted at the front of the vehicle. Two neural network learning strategies: backpropagation and reinforcement learning, are examined in a simulation and compared with respect to learning speed, capacity of tracking and the effort required to adapt the control networks of the real vehicle.<>