Analysis of Automatic Collision Avoidance Strategy for Unmanned Surface Vessel

A novel intelligent collision avoidance algorithm based on deep reinforcement learning approach for USV

To ensure navigation safety, unmanned surface vehicles (USVs) need to have autonomous collision avoidance capability. A large number of studies on ship collision avoidance are available, and most of these papers assume that the target ships keep straight or follows the International Regulations for Preventing Collisions at Sea (COLREGS). However, in the actual navigation process, the target ship may temporarily turn. Based on the above reasons, this paper proposes a multi-ship collision avoidance decision method for USVs based on the improved velocity obstacle algorithm. In the basic dynamic ship domain model, a collision risk model is constructed to improve the accuracy of the risk assessment between the USV and target ships. The velocity obstacle algorithm is combined with the dynamic ship domain, and the collision avoidance timing and method are judged according to the collision risk. The simulation results show that the decision method can handle the situation that the target ship temporarily turns and has an emergency collision avoidance capability. Compared with the traditional VO algorithm, the collision avoidance time of the method is shorter, and the number of course changes is less.

During the process of collision avoidance, especially in a multi-ship encounter situation, the dynamic interactions among individual ships impose a significant impact on collision avoidance decision-making. It is imperative, therefore, that collision avoidance decisions are formulated with a comprehensive consideration of not only the current direct collision conflict but also the potential conflicts due to planned collision avoidance actions. To address this requirement, this paper proposes a dynamic conflict cluster detection method for collision avoidance decision-making in multi-ship encounters. The involved ships are clustered into stable temporal-dependent ship conflict groups taking into account both conflict connectivity and the potential spatiotemporal interactions originating from planned collision avoidance actions. The conflict cluster detection model is implemented within a framework to achieve hierarchical coordinated collision avoidance decision-making. By a simulation experiment of an 11-ship encounter, the proposed method successfully discerns the ships with conflicts and provides feasible collision avoidance decisions. Compared to the non-cluster collision avoidance methods, the proposed method generates the results with acceptable deviating distance and number of collision avoidance actions at minimum computation load. It has been demonstrated that the proposed method is both effective and efficient for officers on board and operators at Vessel Traffic Services centers in real-life navigation.

This study aims to solve the problem of intelligent collision avoidance of unmanned ships at sea, and it proposes a novel driving strategy generating method of collision avoidance based on an extensive-form game mode with fuzzy credibility numbers. The innovation of this study is to propose an extensive-form game model of unmanned ships under the situation of two-sides clamping and verify the validity by fuzzy credibility. Firstly, this study divides the head-on situation of the ship at sea quantitatively to help the unmanned ship take targeted measures when making collision avoidance decisions. Secondly, this study adopts an extensive-form game model to model the problem of collision avoidance of an unmanned ship in the case of clamping on two sides. Thirdly, the extensive-form game model is organically combined with the fuzzy credibility degree to judge whether the collision avoidance game of unmanned ship achieves the optimal collision avoidance result. The effectiveness of the introduced game model is verified by case analysis and simulation. Finally, an illustrative example shows that the proposed mathematical model can better help unmanned ships make real-time game decisions at sea in the scenario of two-sides clamping effectively.

It is crucial to develop a COLREGs-compliant intelligent collision avoidance system for the safety of unmanned ships during navigation. This paper proposes a collision avoidance decision approach based on the deep reinforcement learning method. A modified collision avoidance framework is developed that takes into consideration the characteristics of different encounter scenarios. Hierarchical reward functions are established to assign reward values to constrain the behavior of the agent. The collision avoidance actions of the agent under different encounter situations are evaluated on the basis of the COLREGs to ensure ship safety and compliance during navigation. The deep Q network algorithm is introduced to train the proposed collision avoidance decision framework, while various simulation experiments are performed to validate the developed collision avoidance model. Results indicate that the proposed method can effectively perform tasks that help ships avoid collisions in different encounter scenarios. The proposed approach is a novel attempt for intelligent collision avoidance decisions of unmanned ships.

The main goal of this paper is to permit the growth of air traffic, whilst maintaining or increasing flight safety levels through automation. This should assist pilots and air traffic controllers and increase aircraft autonomy. MAGENTA is a PhD thesis, providing a framework for developing automatic learning tools. This framework has proven to be suitable for the aeronautic environment because of its adaptability to dynamic environments. One objective is to automate present aircraft collision avoidance systems. Collision avoidance refers here to a variety of possible occurrences, including other aircraft, geography, buildings, and so on. Another specific objective is optimize present automatic steering systems, by means of which aircraft can follow a specific or select the best route from a starting point to the head of the runway at the destination airport. These two objectives are in line with currentFree FlightandFree Routeplans in both the United States and Europe. This paper includes testing these automatic steering, navigation and collision avoidance capabilities with a flight simulator in a similar way to how pilots learn and are tested.

In this paper, the intelligent cooperative control problem of unmanned surface vehicles (USVs) is investigated. We consider a team of USVs used in the protection of a target against potential threats. The task of the USVs is to cooperatively protect the target from being destroyed. A behavior-based fuzzy logic control system is presented to solve the problem. First, we identify two types of behaviors; low and high level behaviors. High level behaviors act as a mechanism to induced coordination and synchronization among USVs. Based on this, four high level behaviors (behavior integrator, intercept, formation and assist behaviors), each implementing a fuzzy inference system and two low level behaviors(collision avoidance and attack behaviors) are proposed. The paper defines behavior-based rules to meet the requirement of a simple operational scenario. Genetic algorithms is used to learn the rule base and the choice of behavior. Simulation results demonstrates the effectiveness of our approach. Results shows that the approach has potential application for a real team of cooperative USVs.

When sailing on cluttered water, effective collision avoidance is an essential safety requirement for unmanned surface vehicles (USVs). So that it can avoid multiple random ships effectively. This paper proposes a collision avoidance strategy for USVs based on the probabilistic game theory framework. First, a probability model is established combined with the USV’s kinematics for the collision avoidance problem. Then a greedy algorithm is designed under the framework of probability. It uses a cost function that searches possible movement paths to determine avoidance strategies for the USV. Compared with other collision avoidance methods, the method in this paper seeks to minimize the collision probability instead of guaranteeing no collision, because it is very difficult or impossible to completely avoid the collision in practice. Based on this, our method copes with kinematic constraints of the USV. The effectiveness of the algorithm is verified by simulation, and the simulation results show that the collision avoidance strategy proposed in this paper achieves a very good collision avoidance performance.

Unmanned Surface Vehicles (USVs) are intelligent machines that have been widely studied in recent years. The safety of USVs’ activities is a priority issue in their applications; one effective method is to delimit an exclusive safety domain around the USV. Besides considering collision avoidance, the safety domain should satisfy the requirements of encounter situations in the COLREGs (International Regulations for Preventing Collisions at Sea) as well. Whereas the model providing the safety domain for the USVs is defined through the experience of the manned ships, a specific model for USVs has been rarely studied. A dynamic navigation safety domain (DNSD) for USVs was proposed in this paper. To construct the model, the essential factors that could affect the navigation safety of the USVs were extracted via a rough set, and the extension functions of these factors were carried out. The DNSD was employed in various situations and compared with the ship domain models of common ships. It was found that the domain boundary can be automatically corrected according to the change in the working conditions when the DNSD is in use. Compared with the Fujii and Coldwell models, the DNSD can provide a larger safety area for a USV’s action of collision avoidance.

The Unmanned Surface Vehicles (USVs) have the characteristics of small volume, fast speed, and its application field is often in unknown complex ocean environment. Therefore, it is necessary to solve the fast collision avoidance problem of USV in unknown ocean environment. To solve this problem, a fast collision avoidance method based on velocity resolution is proposed. The motion constraint of the USV in the method is mainly based on the Lanxin USV of Dalian Maritime University. Finally, the safety and rapidity of the method are verified in the complex static and dynamic environments, which can provide a reference for the research of collision avoidance technology about USV.

Safe cooperative path following with relative-angle-based collision avoidance for multiple underactuated autonomous surface vehicles

COLREGs-abiding hybrid collision avoidance algorithm based on deep reinforcement learning for USVs

Unmanned surface vehicle (USV) has witnessed a rapid growth in the recent decade and has been applied in various practical applications in both military and civilian domains. USVs can either be deployed as a single unit or multiple vehicles in a fleet to conduct ocean missions. Central to the control of USV and USV formations, path planning is the key technology that ensures the navigation safety by generating collision free trajectories. Compared with conventional path planning algorithms, the deep reinforcement learning (RL) based planning algorithms provides a new resolution by integrating a high-level artificial intelligence. This work investigates the application of deep reinforcement learning algorithms for USV and USV formation path planning with specific focus on a reliable obstacle avoidance in constrained maritime environments. For single USV planning, with the primary aim being to calculate a shortest collision avoiding path, the designed RL path planning algorithm is able to solve other complex issues such as the compliance with vehicle motion constraints. The USV formation maintenance algorithm is capable of calculating suitable paths for the formation and retain the formation shape robustly or vary shapes where necessary, which is promising to assist with the navigation in environments with cluttered obstacles. The developed three sets of algorithms are validated and tested in computer-based simulations and practical maritime environments extracted from real harbour areas in the UK.

In order to improve the effectiveness of intelligent collision avoidance decision of ships, a collision avoidance decision model is established with the objective of guaranteeing the safety of ship navigation and reducing the loss of voyage, taking real-time data as the input quantity and the requirements of international maritime collision avoidance rules and the common practice of seafarers as the constraints, and MOEA/D (Multi-objective Evolutionary Algorithm Based on Decomposition) algorithm is used to optimize the objective function and calculate the optimal steering angle and steering timing. The simulation results show that the decision can meet the safety and economic requirements of ship collision avoidance under different encounter situations and can provide some reference for ship collision avoidance decision.

Coordinated multi-stage and multi-objective optimization approach for ship collision avoidance decision-making