Marine Vessel Auto-Docking Using ML-Guided Path Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing auto-docking systems for marine vessels are slower compared to human pilots, necessitating improvements for efficient and accurate automated docking processes.
Innovation Solution
A computer-implemented method using a machine learning model to predict initial control parameters and a collision-free path, combined with an optimization function to minimize time and energy consumption, trained on datasets from human operators in various environments, to enhance auto-docking efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If traditional optimization methods are used for auto-docking control, then the system can achieve docking functionality, but the docking process is too slow compared to human pilots
Solution Approach 1:
The system performs preliminary actions by training a machine learning model offline using datasets from human pilots before actual docking operations. The model learns optimal control parameters in advance, enabling fast real-time docking decisions without requiring complex online optimization calculations
Solution Approach 2:
The patent replaces traditional mechanical optimization algorithms with a machine learning-based neural network model. This substitution enables the system to achieve human-pilot-level docking speeds by using learned patterns instead of computationally intensive real-time optimization
2Measurement precision
If complex optimization functions are used to minimize energy consumption and time, then the accuracy of control parameters improves, but the computational time increases
Solution Approach 1:
The system performs the complex optimization work in advance during the offline training phase. The neural network model learns the relationship between docking conditions and optimal control parameters through extensive pre-computation, allowing fast accurate predictions during actual docking operations
Solution Approach 2:
The machine learning model creates a simplified copy of the complex optimization function. Instead of executing the full optimization algorithm in real-time, the system uses the trained model which captures the essential relationships, providing accurate results with minimal computational overhead
Data Source
AI summary
A computer-implemented method for generating control parameters for auto-docking of a marine vessel, and to a control unit for executing the method, to a marine vessel including the control unit, and to a corresponding computer program product.