Solving quay wall allocation problems based on deep reinforcement learning

Abstract Quay walls and graving docks are critical production resources in shipyards. Traditionally, quay walls have not been a bottleneck resource for constructing conventional vessels, such as oil carriers and container ships. However, the growing demand for high value-added vessels requiring more complex post-stage outfitting operations has increased workloads at quay walls. Accordingly, the importance […]

Adaptive Enhancement of an Active Sonar Classifier Using Mode-Connectivity-Based Fine-Tuning Under Data Set Shifts

Abstract In supervised-learning-based active sonar classification overcoming data set shifts through standard fine-tuning is challenging due to the limited size and diversity of active sonar data sets. To address this challenge, we propose a robust fine-tuning method using mode connectivity (RoFT-MC), which mitigates two key problems in standard fine-tuning: catastrophic forgetting and negative transfer. RoFT-MC […]

Optimization and economic evaluation of carbon dioxide BOG Re-liquefaction process considering storage pressure and nitrogen impurity

Abstract The increasing demand for carbon capture and storage (CCS) has heightened the need for liquefied carbon dioxide (LCO2) carriers, which require re-liquefaction systems to manage boil-off gas (BOG) generated during transportation. This study proposed new two-stage separation re-liquefaction processes with mixed refrigerants for CO2 BOG containing nitrogen impurity. The proposed processes were evaluated and compared […]

Off-axial force and moment modeling of a marine propeller in oblique inflow by URANSE simulation

Abstract A prediction model for the off-axial hydrodynamic forces and moments of a screw propeller working behind a hull in maneuvering and seakeeping is proposed by computational fluid dynamics analysis. The data for modeling are acquired via propeller open water simulations in oblique inflow conditions, considering changes in axial and transverse inflow speed, propeller diameter, […]

Improving Pose Graph Optimization via Efficient Graduated Non-convexity Scheduling

Abstract In this study, we propose a novel approach to graduated non-convexity (GNC) and demonstrate its efficacy through its application in robust pose graph optimization, a key component in SLAM backends. Traditional GNC methods rely on heuristic methods for GNC schedule, updating control parameter μ for escalating the non-convexity. However, our approach leverages the properties of convex […]

Probabilistic Kernel Optimization for Robust State Estimation

Abstract Robust state estimation is a fundamental research topic in robotics. Existing approaches like robust kernels combined with iteratively re-weighted least squares (IRLS) often require heuristic parameter selection and extensive fine-tuning. In this manuscript, we propose a novel method that optimizes kernels while preserving the advantages of existing techniques. By introducing a probabilistic interpretation of […]

Elastic shakedown limit analysis of sleeve-reinforced 90° back-to-back pipe bends with local wall thinning under cyclic in-plane bending moment and steady internal pressures

Abstract This study presents the elastic shakedown limit of a sleeve-reinforced 90° back-to-back pipe bends structure with local wall thinning, using the finite element method. In this study, the sleeve-reinforcement is inspired by double-walled piping systems that have been popularly applied to pipelines carrying hazardous fluids. A three-dimensional finite element model is created to investigate […]