Intelligent modelling and control for autonomous systems

Summary form only given. The demand for long mission duration, associated reliability and availability requirements, operation in unstructured environments, real time operating requirements, and flexibility of use has led to increasing levels of autonomy in underwater vehicles. Aspects of multi-sensor data fusion for vehicle localisation and obstacle detection, together with developments in estimation algorithms are covered in this paper. We illustrate AUV modelling and control which enables both performance and robustness criteria to be satisfied by utilising neuro-fuzzy methods and online data gathering via the sensor bed.