Hierarchical control of marine vehicles for autonomous manoeuvring in offshore operations

This paper presents a hierarchical control scheme that can achieve autonomous manoeuvring for marine vehicles in offshore operations. Different from dynamic positioning problems, fine manoeuvring not only requests low speed of vessels and high control accuracy but also has very strict and limited working spaces during offshore operations, such as oil platform maintenance, seabed survey and pipeline installations. To address fine manoeuvring, a two-level control architecture is proposed with an emphasis on developing autonomous manoeuvring from a specific application to final thrust allocation. On the high level, a ship controller is designed for regulation and dynamic positioning of ships. Thanks to the function approximation capabilities of neural networks, the controller is able to force the ship to desired targets with unknown dynamics of the ship. A thrust allocator is further developed on the low level that distributes control forces to individual actuators while satisfying optimising constraints. By linearising the constraints and employing the quadratic programming (QP) approach, an optimised thrust allocation is obtained. Both the ship controller and the thrust allocator are verified by simulation with the Cybership II model. The results confirm the effectiveness of the proposed hierarchical control scheme.