This paper studies the problem of controlling the movements of a handicappe
d person's motorized wheelchair from a practical point of view. The control
system implemented has been divided into two levels: the "low level", cons
isting of an electronic system which directly controls the drivers of the c
hair's motors, with a classic PID (proportional-integral-derivative) contro
l loop. The aim of this level is to ensure that the speeds of each one of t
he wheels is similar to the input speed of these control boards. The second
control level ("high level"), implemented by means of neural techniques, e
nsures that the linear and angular speeds of the wheelchair are those indic
ated by a trajectory generator. A new recurrent model is used as the neural
network, for which the stability conditions of the complete control system
are obtained and various practical tests are carried out, which show the c
orrect performance of the actual system implemented.