Neurointerfaces - Control Systems Technology, IEEE Transactions on

A neurointerface is a nonlinear filtering system based on neural networks (NNs) that serves as a coupler between a human operator and a nonlinear system or plant that is to be controlled or directed. The purpose of the coupler is to ease the task of the human controller. The equations of the plant are assumed to be known. If the plant is unstable, it must first be stabilized by feedback. Using the plant equations, off-line automatic learning algorithms are developed for training the weights of the neurointerface and the weights of an adaptive plant disturbance canceller. Application of these ideas to backing a truck with two trailers under human direction is described. The “truck backer” has been successfully demonstrated by computer simulation and by physical implementation with a small radio-controlled truck and trailers.