Learning and adaptive neural controller

A neural learning and adaptive scheme, called inverse-dynamics adaptive control (IDAC) is presented. The IDAC scheme provides a learn-while-functioning capability. The error signal, defined as a difference between the desired and the actual outputs, modifies the controller weights until the controller structure becomes an approximate inverse-dynamics model of the process under control, making the transfer function from output-to-input unity. The necessary learning and adaptive algorithm is derived, and the computer simulation results to evaluate the performance of the IDAC algorithm are presented