In this paper, a hybrid intelligent method including fuzzy inference and ne
ural network is presented for real-time self-reaction of a mobile robot in
unknown environments. A neural network with fuzzy inference (fuzzy neural n
etwork, FNN) presented can effectively improve the learning speed of the ne
ural network. The method can be used to control a mobile robot based on the
present motion situations of the robot in real-time, these situations incl
ude the distances in different directions between the obstacles and the rob
ot provided by ultrasonic sensors. the target orientation sensed by a simpl
e optical range-finder and the movement direction of the robot. Simulation
results showed that the above method can quickly map the fuzzy relationship
between the inputs and the output of the control system of the mobile robo
t. (C) 2001 Elsevier Science Ltd. All rights reserved.