Adaptive control in nonlinear dynamic systems with inherent delays

Summary form only given. A small robot arm has been used to study the use of neural networks as adaptive controllers and neural emulators. The objectives were to investigate nonlinear systems that are accompanied by large time delays. Such systems can be difficult to control, since delays in feedback loops often give rise to instabilities. Neural network emulators have been used to simulate the operation of this system using a database of dynamic stimulus-response. Conventional methods of indirect learning (back-propagating errors through the emulator) to train an inverse kinematic feedforward controller do not work for such systems. Instead, it is necessary to provide the controller with the capability to anticipate future target trajectories