AIS-Derived Maritime Routing Graph with Collaborative Fleet Learning

Key Points

• The research aims to develop a maritime routing system that utilizes AIS data to create an optimal routing graph for vessels.
• Constructed a waypoint graph from AIS vessel track data using Douglas-Peucker compression.
• Implemented Fleet Collaborative Route Consensus for real-time route sharing among vessels.
• Applied zone-stratified AIS compression to achieve significant storage reduction.
• Enabled vessel-type-aware graph traversal considering draft, length, and beam constraints.
• Achieved a median error of 1.2%, compared to 30-50% for traditional straight-line methods.
• Demonstrated a 99% reduction in storage requirements while maintaining over 95% accuracy.
• Utilized over 52 million AIS positions across 36,000 vessels and 12,714 ports.