Ship Collision Avoidance Algorithm Performance Metrics

5.5 KB of experimental results comparing a proposed multi-agent game-theory algorithm for ship collision avoidance. The dataset likely contains key performance indicators such as collision rate, COLREGs compliance rate, trajectory smoothness, and average risk, derived from simulations using historical AIS data. It was authored by Tie Xu and last updated on June 3, 2026.

Use Cases

• Benchmarking collision avoidance algorithms based on reported metrics like collision rate and COLREGs compliance rate.
• Evaluating the impact of integrating risk attitude perception layers, as described using LSTM networks and Bayesian inference.
• Studying the performance of multi-agent reinforcement learning frameworks in dynamic, multi-ship environments.
• Analyzing the effect of embedding regulatory rules as constraints in an action space on algorithm compliance.

Strengths

• The dataset is associated with a detailed methodological description involving LSTM networks, Bayesian inference, and Stackelberg games.
• Results include multiple key performance indicators, suggesting a structured evaluation framework.
• The data is licensed under CC-BY-4.0, allowing for open reuse.

Limitations

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

Provenance

Source

figshare, authored by Tie Xu.

Collection Method

Experimental verification based on historical AIS data and simulation scenarios.

Freshness

Last updated 2026-06-03 17:40:24; freshness should be verified.