Neurofuzzy prediction for gaze control

Real-time gaze control is a complicated task because of the different dynamics of the elements involved in the process. On the one hand, the algorithms for image processing are usually very time-consuming. On the other hand, the motors and mechanisms used to control camera movements are very slow. This work describes the use of an adaptive network-based fuzzy inference system (ANFIS) model to reduce the delay effects in gaze control and also explains how the delay problem is resolved through prediction of the target movement using a neurofuzzy approach. The approach has been successfully tested in the vision system of a humanoid robot. The predictions improve the velocity and accuracy of object tracking.