A5047313376- Ship Hydrodynamics and Maneuverability
- Fluid Dynamics Simulations and Interactions
- Maritime Navigation and Safety
- Structural Integrity and Reliability Analysis
- Ocean Waves and Remote Sensing
- Maritime Transport Emissions and Efficiency
- Probabilistic and Robust Engineering Design
- Adaptive Control of Nonlinear Systems
- Robotic Path Planning Algorithms
- Underwater Vehicles and Communication Systems
- Marine and Coastal Research
- Maritime Ports and Logistics
- Control and Dynamics of Mobile Robots
- Distributed Control Multi-Agent Systems
- Wave and Wind Energy Systems
- Inertial Sensor and Navigation
- Optimization and Search Problems
- Chaos control and synchronization
- Structural Health Monitoring Techniques
- Guidance and Control Systems
- Quantum chaos and dynamical systems
- Vibration and Dynamic Analysis
- Target Tracking and Data Fusion in Sensor Networks
- Metaheuristic Optimization Algorithms Research
- Hydraulic and Pneumatic Systems
Osaka University
2008-2025
RIKEN Center for Advanced Intelligence Project
2021
University of Tsukuba
2021
Acquisition, Technology & Logistics Agency
2017
Naval Surface Warfare Center
2016
Ministry of Defence
2014-2015
National Defense Academy of Japan
2015
Kobe University
2009-2014
Research & Development Institute
2011
Although various studies have been conducted on automatic berthing, including offline optimization and online control, real-time berthing control remains a difficult problem. Online methods without reference trajectories are promising for control. We used reinforcement learning (RL), which is type of machine learning, to obtain an law trajectories. As difficult, obtaining appropriate with naive difficult. Furthermore, almost all existing do not consider port geometries. This study proposes...
Abstract Numerous accidents caused by parametric rolling have been reported on container ships and pure car carriers (PCCs). Considering this dangerous phenomenon, the in irregular seas is examined paper based stability of systems origin, which corresponds to upright condition vessel. It provides a novel theoretical explanation instability mechanism for two cases: white-noise excitation colored-noise excitation. Moreover, authors confirm usefulness previously provided formulae Roberts Dostal...
We propose an approach to saddle point optimization relying only on oracles that solve minimization problems approximately. analyze its convergence property a strongly convex–concave problem and show linear toward the global min–max point. Based analysis, we develop heuristic adapt learning rate. An implementation of developed using (1+1)-CMA-ES as oracle, namely, Adversarial-CMA-ES, is shown outperform several existing approaches test problems. Numerical evaluation confirms tightness...
Abstract Automation of berthing maneuvers in shipping is a pressing issue as the maneuver one most stressful tasks seafarers undertake. Berthing control problems are often tackled by tracking predefined trajectory or path. Maintaining error zero under an uncertain environment impossible; controller nonetheless required to bring vessels close desired berths. The must prioritize avoidance errors that may cause collisions with obstacles. This paper proposes training method based on...
Abstract For the ship stability estimation and design, it is helpful to know probability of roll amplitude exceeding a certain threshold. Therefore, necessary obtain density function amplitude. In this study, first, we derive moment values by combining equations linearity expectation. With this, propose method estimate using obtained values. The results our proposed are compared those from Monte Carlo simulations. When higher-order cumulant neglect closure used, resulting close corresponding...
Abstract A simulation environment of harbor maneuvers is critical for developing automatic berthing. Mathematical models are widely used to estimate maneuvers. However, user’s analysis and decision necessary derive, select, identify the model because each actuator configuration needs an inherent mathematical expression. We proposed a new arbitrary configurations overcome that issue. The hybrid combines simplicity derivation Taylor expansion high degree freedom MMG low-speed maneuvering...
Abstract A dynamic model for an automatic berthing and unberthing controller has to estimate harbor maneuvers, which include berthing, unberthing, approaching maneuvers berths, entering leaving the port. When is estimated by system identification using feedforward neural networks, a large number of tests or trials are required measure various motions maneuvers. However, amount data that can be obtained limited due high costs time-consuming nature full-scale ship trials. Therefore, this paper...