Ship Encounter Patterns for Collision Avoidance Algorithm Testing

Historical Automatic Identification System (AIS) data used to verify a ship collision avoidance algorithm. The dataset, created by Tie Xu and last updated in June 2026, supports testing of a multi-agent reinforcement learning framework. It likely contains encounter characteristics and inferred risk attitudes derived from AIS data.

Use Cases

• Testing reinforcement learning algorithms for ship collision avoidance based on historical AIS trajectories.
• Analyzing multi-ship encounter patterns and coupling risks mentioned in the description.
• Evaluating COLREGs compliance rates in simulated navigation scenarios.
• Training risk attitude prediction models using Bayesian inference on encounter data.

Strengths

• Data is licensed under CC-BY-4.0, allowing for open use and redistribution.
• Dataset is associated with a published research paper describing a specific algorithm verification methodology.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Dataset size is 5.5 KB, indicating a very limited scope.

Provenance

Source

figshare

Collection Method

Likely derived from historical Automatic Identification System (AIS) data.

Freshness

Last updated 2026-06-03 17:40:22; freshness should be verified.