THE ADAPTIVE-CONTROL OF A 4-DEGREES-OF-FREEDOM STEREO CAMERA HEAD

The paper describes the use of biologically plausible neural network architectures to address some of the issues associated with the use of stereopsis under variable camera geometry. We report an implementation of a layered (subsumption) architecture for the adaptive control of microsaccadic tracking, and show experimental results demonstrating the use of lattice filter predictors for trajectory modelling. A rather simple, but seemingly adequate, neural network architecture for representing high-dimensional surface approximations (PILUTS) is evaluated as a method of encoding the predictive stereo mapping of the ground plane for different head positions.