Vessel Navigation Rule Estimation for Transparent Collision Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems fail to clearly clarify actions that comply with various rules applicable to vessel navigation and the reasons for those determinations, often lacking reliability and failing to consider differences in rules based on surrounding conditions, leading to potential safety issues and non-compliance with legal regulations.
Innovation Solution
A navigation assistance system that includes a rule estimation logic storage, own ship and target data acquirers, situational awareness data generator, relative relationship specifier, and rule estimator to determine applicable rules based on the relative relationship between the own ship and targets, ensuring compliance with COLREG and other navigation rules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional collision avoidance route suggestion technologies are used, then collision avoidance routes can be provided, but the actions and reasons for compliance with navigation rules are not clearly clarified
Solution Approach 1:
The system segments the complex task of rule compliance analysis into distinct functional modules: rule estimation logic storage, own ship setting data storage, situational awareness data generation, relative relationship specification, and rule estimation. Each module handles a specific aspect of the analysis, making the overall system more manageable and transparent while clearly clarifying the actions and reasons for rule compliance.
2Reliability
If collision avoidance routes are generated without considering surrounding conditions, then route generation is simplified, but compliance with navigation rules cannot be ensured
Solution Approach 1:
The system performs preliminary actions by storing rule estimation logic and own ship setting data in advance, and by generating situational awareness data before rule estimation. This preliminary processing ensures that when collision avoidance routes are generated, the system already has the necessary contextual information about surrounding conditions, water areas, and visibility states to ensure rule compliance reliability.
3Extent of automation
If AI is used for decision-making from target detection to collision avoidance, then automation is improved, but the processes and reasons become a black box and unclear
Solution Approach 1:
The system implements feedback by generating situational awareness data that explicitly captures the state of surrounding conditions, water area characteristics, and visibility. This feedback loop ensures that the automated decision-making process is transparent, as the rule estimator can trace back through the situational awareness data to understand the reasons for its recommendations, preventing the black box problem.
4Ease of operation
If navigation rules are applied without considering water area and weather conditions, then rule application is simplified, but safety and compliance cannot be guaranteed
Solution Approach 1:
The system applies local quality by storing and processing own ship setting data that includes specific parameters for different water areas and weather conditions. The rule estimation logic is tailored to local conditions, allowing the system to automatically adapt the application of navigation rules based on the specific situation, thereby maintaining both ease of operation and reliability.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A navigation assistance system (1) stores therein rule estimation logic for estimating a relationship in application of a rule to conduct of a vessel, and own ship setting data including a parameter indicating a characteristic of an own ship, and acquires own ship data indicating information on a state of the own ship, acquires target data indicating information on a state of a target, acquires surrounding data indicating information on a state of surrounding of the own ship, generates situational awareness data indicating a situation for determining an action of the own ship, based on the own ship data, the target data, and the surrounding data, specifies a relative relationship between the own ship and the target, based on the situational awareness data, and estimates an applicable rule to be applied to the own ship, based on the specified relative relationship and the own ship setting data, in accordance with the rule estimation logic.