Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

Papadimitrakis, Myron; Stogiannos, Marios; Sarimveis, Haralambos; Alexandridis, Alex

doi:10.3390/s21216959

Cited by 17 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The technique could automatically generate a ship's path based on its various dimensions. In the research of Gan et al [52], the well-known K-Means clustering approach was used to first group the historical trajectories. Next, ANN models were constructed to forecast the trajectories of the ships using the above clustering results together with other known factors (such as ship speed, loading capacity, self-weight, maximum power, and water level).…”

Section: Hybrid Of Neural Network and Other Algorithmsmentioning

confidence: 99%

Artificial Intelligence in Ship Trajectory Prediction

Bi,

Cheng,

Zhang

et al. 2024

JMSE

View full text Add to dashboard Cite

Maritime traffic is increasing more and more, creating more complex navigation environments for ships. Ship trajectory prediction based on historical AIS data is a vital method of reducing navigation risks and enhancing the efficiency of maritime traffic control. At present, employing machine learning or deep learning techniques to construct predictive models based on AIS data has become a focal point in ship trajectory prediction research. This paper systematically evaluates various trajectory prediction methods, spanning classical machine learning approaches and emerging deep learning techniques, to uncover their respective merits and drawbacks. In this work, a variety of studies were investigated that applied different algorithms in ship trajectory prediction, including regression models (RMs), artificial neural networks (ANNs), Kalman filtering (KF), and random forests (RFs) in machine learning, along with deep learning such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory (LSTM), gate recurrent unit (GRU) networks, and sequence-to-sequence (Seq2seq) networks. The performance of predictive models based on different algorithms in trajectory prediction tasks was graded and analyzed. Among the existing studies, deep learning methods exhibit significant performance and considerable potential application value for maritime traffic systems, which can be assessed by future work on ship trajectory prediction research.

show abstract

Section: Hybrid Of Neural Network and Other Algorithmsmentioning

confidence: 99%

Artificial Intelligence in Ship Trajectory Prediction

Bi,

Cheng,

Zhang

et al. 2024

JMSE

View full text Add to dashboard Cite

show abstract

“…The first category of methods is based on analytical models. This category of algorithms describes the ship's movement and its surroundings with an accurate mathematical model, such as MPC [5], VO [6,7], and APF [8]. Although these algorithms are effective, they often lack the flexibility to cope with complex and dynamic environments.…”

Section: Literature Reviewmentioning

confidence: 99%

“…At the same time, the rudder angle is calculated by the PD controller and solved by the differential equation, as expressed in Equations ( 3)- (5).…”

Section: Action Spacementioning

confidence: 99%

A Multi-Ship Collision Avoidance Algorithm Using Data-Driven Multi-Agent Deep Reinforcement Learning

Niu,

Zhu,

Wei

et al. 2023

JMSE

View full text Add to dashboard Cite

Maritime Autonomous Surface Ships (MASS) are becoming of interest to the maritime sector and are also on the agenda of the International Maritime Organization (IMO). With the boom in global maritime traffic, the number of ships is increasing rapidly. The use of intelligent technology to achieve autonomous collision avoidance is a hot issue widely discussed in the industry. In the endeavor to solve this problem, multi-ship coordinated collision avoidance has become a crucial challenge. This paper proposes a multi-ship autonomous collision avoidance decision-making algorithm by a data-driven method and adopts the Multi-agent Deep Reinforcement Learning (MADRL) framework for its design. Firstly, the overall framework of this paper and its components follow the principle of “reality as primary and simulation as supplementary”, so a real data-driven AIS (Automatic Identification System) dominates the model construction. Secondly, the agent’s observation state is determined by quantifying the hazardous area. Then, based on a full understanding of the International Regulations for Preventing Collisions at Sea (COLREGs) and the preliminary data collection, this paper combines the statistical results of the real water traffic data to guide and design the algorithm framework and selects the representative influencing factors to be designed in the collision avoidance decision-making algorithm’s reward function. Next, we train the algorithmic model using both real data and simulation data. Meanwhile, Prioritized Experience Replay (PER) is adopted to accelerate the model’s learning efficiency. Finally, 40 encounter scenarios are designed and extended to verify the algorithm performance based on the idea of the Imazu problem. The experimental results show that this algorithm can efficiently make a ship collision avoidance decision in compliance with COLREGs. Multi-agent learning through shared network policies can ensure that the agents pass beyond the safe distance in unknown environments. We can apply the trained model to the system with different numbers of agents to provide a reference for the research of autonomous collision avoidance in ships.

show abstract

“…The RBF neural network, as a machine learning method, has a strong fitting ability [37]. It generates a high-precision model by using real data [38]. Compared with other neural networks, it has the following merits: a strong approximation ability, simple network structure, and rapid learning speed [39,40].…”

Section: Introductionmentioning

confidence: 99%

Exploring Development Trends of Terrestrial Ecosystem Health—A Case Study from China

Zhang

et al. 2021

Land

View full text Add to dashboard Cite

Terrestrial ecosystem health (TEH) is the basis of regional sustainability development. The state of TEH is an important research direction in the land science field. The purpose of this paper was to explore the development trends and influencing factors of the. By using the radial basis function (RBF), neural network model, geographic information system (GIS), and the comprehensive index method, this paper predicted the land ecological changes of Henan Province from 2007 to 2025 based on a comprehensive evaluation of the system. The results show that the TEH of Henan Province exhibited a general trend of improvement from 2007 to 2025. The predictions exhibited a tendency to fluctuate and increase, from “severe warning” to “moderate warning” and even to “no warning” state. The early warning index of the subsystem showed a fluctuating upward trend except for the press subsystem, which fluctuated between “extraordinary warning” and “heavy warning” states. The overall TEH level is improving but is largely dependent on effective corresponding measures. The health status of the land ecosystem in Henan Province is guaranteed to be stable due to improvements in rural residential incomes, mechanization levels of cultivated land, domestic sewage treatment rates, and the numbers of scientific and technological personnel per unit of land. The TEH is mainly restricted by the population densities, urbanization levels, inputs of fertilizers and pesticides, and average wastewater load factors of the land. To improve the health level of the land ecosystem, it is necessary to reduce the use of fertilizers and pesticides and to control the urbanization rate. At the same time, improving the level of forest coverage and the effective irrigation rate play a positive role in improving ecosystem health. The results provide a reference for land-use planning and management decisions.

show abstract

Multi-Ship Control and Collision Avoidance Using MPC and RBF-Based Trajectory Predictions

Cited by 17 publications

References 50 publications

Artificial Intelligence in Ship Trajectory Prediction

Artificial Intelligence in Ship Trajectory Prediction

A Multi-Ship Collision Avoidance Algorithm Using Data-Driven Multi-Agent Deep Reinforcement Learning

Exploring Development Trends of Terrestrial Ecosystem Health—A Case Study from China

Contact Info

Product

Resources

About