With the continuous progress of contemporary science and technology and the increasing requirements for marine vehicles in various fields, the intelligence and automation of ships have become a general trend. The autonomous control of surface Unmanned Surface Vessel (USV) generally covers the USV path planning, path tracking control, and autonomous collision avoidance control. But in the whole navigation process of USV, autonomous berthing is also a crucial part. And the research on the algorithm of the automatic berthing process of the USV is less. Mature USV autonomous berthing technology can effectively reduce the cost of human and material resources and financial resources while reducing the accident rate reasonably and safely. Therefore, it is of great importance to comprehensively promote the development of USV autonomous berthing technology.

In recent years, the research of multiple unmanned surface vessels collaboration has received great attention. More and more researchers have proposed different methods of multiple unmanned surface vessels collaboration, such as cooperative collision avoidance, formation, and rendezvous. Based on the significant advantages of biological swarm intelligence applications in these collaborative methods, this article summarizes the research methods of multiple unmanned surface vessels collaborative search and hunting from the perspective of swarm intelligence. First of all, this article summarizes the key technologies of multiple unmanned surface vessels collaborative search and hunting from the aspects of the multi-robot system, group communication, environment modeling, collaboration mechanism, and path planning. Then, it reviews some classic swarm intelligence algorithms, analyzes the advantages and disadvantages of these algorithms, and proposes optimization directions for existing disadvantages based on relevant literature. Finally, the article points out some existing problems in every stage and suggestions for future research.

The towing operation of multi-tug-assisted ship navigation mainly relies on the experience of the captain, and there is no set of effective operation methods. Therefore, it is difficult to achieve accurate assisted navigation when multiple tugboats work in coordination. The calculation method of maneuverability of the towing system with multi-tug-assisted navigation is proposed in this paper. In view of the complexity of multi-tug-assisted large ship maneuvering, this article focuses on solving the problems of force analysis and maneuvering modeling between the multi-tug and ship systems. Firstly, a maneuvering mathematic model for towing ships is established, and the hydrodynamic force of the hull, rope force of the tugs, and force of wind interference are analyzed. The thrust and moment of the ducted azimuthal propeller are calculated, and the mathematical model of the tug’s cable tension is discussed. Then, the fourth-order Runge–Kutta method is used to solve the differential equations of the maneuvering motion of the ships and each tug. Based on the ship-towing process by multiple tugs, a multi-tug-assisted ship towing simulation platform was built by using the Visual Studio development tool. Finally, on the simulation platform, multi-tug longitudinal-towing-simulation experiments at different speeds were carried out, and the simulation of turning towing maneuvers under the influence of wind was done. The simulation results showed that as the towing speed increases, the initial towing speed fluctuates greatly. There is a significant drift effect on the ships by the wind force. And the wind will cause a fluctuation in the tug’s rope force. The simulation of the multi-tugs towing a ship entering the port was carried out in the port environment. The results showed that the multi-tug towing system and simulation platform may be used for the safety training of the tug’s crew.

Complete Coverage Path Planning (CCPP) is a key technology for Unmanned Surface Vehicles (USVs) that require complete coverage on the water surface, such as water sample collection, garbage collection, water field patrol, etc. When facing complex and irregular boundaries, the traditional CCPP-based boustrophedon method may encounter many problems and challenges, such as multiple repeated regions, multiple turns, and the easy occurrence of local optima. The traditional genetic algorithm also has some shortcomings. The fixed fitness function, mutation operator and crossover operator are not conducive to the evolution of the population and the production of better offspring. In order to solve the above problems, this paper proposes a CCPP method based on an improved genetic algorithm, including a stretched fitness function, an adaptive mutation operator, and a crossover operator. The algorithm combines the key operators in the fireworks algorithm. Then, the turning and obstacle avoidance during the operation of the Unmanned Surface Vehicle are optimized. Simulation and experiments show that the improved genetic algorithm has higher performance than the exact unit decomposition method and the traditional genetic algorithm, and has more advantages in reducing the coverage path length and repeating the coverage area. This proves that the proposed CCPP method has strong adaptability to the environment and has practical application value in improving the efficiency and quality of USV related operations.

It is crucial for unmanned surface vessels (USVs) to detect and track surrounding vessels in real time to avoid collisions at sea. However, the harsh maritime environment poses great challenges to multitarget tracking (MTT). In this paper, a novel tracking by detection framework that integrates the multimodel and multicue (M³C) pipeline is proposed, which aims at improving the detection and tracking performance. Regarding the multimodel, we predicted the maneuver probability of a target vessel via the gated recurrent unit (GRU) model with an attention mechanism, and fused their respective outputs as the output of a kinematic filter. We developed a hybrid affinity model based on multi cues, such as the motion, appearance, and attitude of the ego vessel in the data association stage. By using the proposed ship re-identification approach, the tracker had the capability of appearance matching via metric learning. Experimental evaluation of two public maritime datasets showed that our method achieved state-of-the-art performance, not only in identity switches (IDS) but also in frame rates.