Neural network algorithm controlling a hexapod platform

An hexapod, or Stewart, platform consists essentially of two platforms and six extensible linear actuators (legs), each one connected to the platforms with a couple of universal joints, one at each end. In the last years several applications have been developed involving a such contrivance and many control systems have been developed. In our case, an astronomical telescope secondary mirror is supported by a hexapod platform and it is complete with its own control system. It is actually functioning on the Telescopio Nazionale Galileo (La Palma Island - Spain). The complete movement-position loop control involve a nonlinear equation system and the basic control algorithm is written using a numerical solution for this non-linear set. In order to permit a better real-time control of the optics, faster algorithms have been explored. Among those, a neural network approach has been studied. Comparison between numerical and neural network performances are reported.