Towards future autonomous tugs: Design and implementation of an intelligent escort control system validated by sea trials

Abstract

Tugs are compact yet powerful watercraft that play an important role in port operations. To enhance efficiency and guarantee operational safety, there is a growing need for the development of autonomous tugs. Aiming to assist human operations, this paper proposes the design and implementation of an intelligent escort control system for tugs, including a model-free planning module and an adaptive motion control method. The model-free planning module consists of path planning, collision avoidance, as well as an improved Logical Virtual Ship (LVS) guidance principle. The adaptive escort control method is implemented via the integrated use of a heading controller and a speed controller, both of which are constructed in a human-like strategy while based on the Model-Free Adaptive Control (MFAC) algorithm. Full-scale simulations are carried out on a marine navigation simulator to evaluate the performance of the proposed planning and control strategy. The sea trials of the escort control system are conducted successfully on a real Azimuth Stern Drive (ASD) tug, the “Jin Gang Lun 36”, at the Rizhao marine test site in China. The experimental results indicate that the system performance is comparable to that of a well-trained human operator maneuvering the tug in escort operations. This could mitigate the workload of human operators, offer important implications for the advancement of autonomous navigation, and serve as a key technology for future autonomous ships.