A5035966314- Maritime Navigation and Safety
- Ship Hydrodynamics and Maneuverability
- Structural Integrity and Reliability Analysis
- Maritime Ports and Logistics
- Maritime Transport Emissions and Efficiency
- Maritime Security and History
- Autonomous Vehicle Technology and Safety
- Robotic Path Planning Algorithms
- Risk and Safety Analysis
- Software Engineering and Design Patterns
- Oil Spill Detection and Mitigation
- Reinforcement Learning in Robotics
- Vehicle Routing Optimization Methods
Wuhan University of Technology
2018-2024
China Ocean Shipping (China)
2023
During the process of collision avoidance, especially in a multi-ship encounter situation, dynamic interactions among individual ships impose significant impact on avoidance decision-making. It is imperative, therefore, that decisions are formulated with comprehensive consideration not only current direct conflict but also potential conflicts due to planned actions. To address this requirement, paper proposes cluster detection method for decision-making encounters. The involved clustered...
Maritime Autonomous Surface Ships (MASSs) are attracting increasing attention in recent years as it brings new opportunities for water transportation. Previous studies aim to propose fully autonomous system on collision avoidance decisions and operations, either focus supporting conflict detection or providing with decisions. However, the human-machine cooperation is essential practice at first stage of automation. An optimized decision-making proposed this paper, which involves risk...
It is crucial to develop a COLREGs-compliant intelligent collision avoidance system for the safety of unmanned ships during navigation. This paper proposes decision approach based on deep reinforcement learning method. A modified framework developed that takes into consideration characteristics different encounter scenarios. Hierarchical reward functions are established assign values constrain behavior agent. The actions agent under situations evaluated basis COLREGs ensure ship and...
It is vital to analyze ship collision risk for preventing collisions and improving safety at sea. This paper takes Ningbo-Zhoushan Port, a typical complex navigable water, as the research object, propose probabilistic conflict detection method estimate potential by using dynamic domain model driven AIS data. Combined with algorithm of fast modularity optimization spectral clustering, group extraction from perspective water navigation management was proposed. Aiming traffic characteristics in...
Maritime traffic situational awareness plays a vital role in developing intelligent transportation support systems. The state-of-the-art research focuses on near-miss collision risk between/among ships. However, it fails to estimate regional situations associated with dynamic and uncertain ship motions at further distances beyond the near misses. This study develops systematic methodology evaluate complexity comprehend situation complex waters. In new methodology, topological evolutionary...
Maritime accidents have become a major threat to societal safety and environmental protection, especially in complex navigable waters with high traffic density diverse ship behaviors. To achieve effective control efficient management, comprehensive understanding of behavior is essential. This study proposed framework for pattern analysis based on multiship encounter detection. The overall methodology incorporates research steps data preprocessing, detection, analysis. Using automatic...
In recent years, the rapid development of mobile technology and application platforms has provided better services for life work. Artificial intelligence have made traffic ever more convenient. As an artificial method that intersects with multiple disciplines fields, reinforcement learning been proved to be highly effective in automatic driving vehicles. However, there are still many difficulties ship collision avoidance, because it involves continuous actions complicated regulations. We...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
It is vital to analyze ship collision risk for preventing collisions and improving safety at sea. This paper takes Ningbo-Zhoushan Port, a typical complex navigable water, as the research object. Firstly, probabilistic conflict detection method based on an AIS data-driven dynamic domain model proposed achieve effective under uncertain environments. Then, group identification proposed, which can extract groups with correlation space compactness. Finally, according characteristics of traffic...