A path planning approach for ship collision avoidance integrating BRB reasoning and velocity obstacle algorithm.

Zheng M; Wang S; Tu H; Lu Q · 2026 · PubMed Central

DOI: 10.1371/journal.pone.0349943

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the challenge of reliable path planning for ship collision avoidance in complex, high-density maritime environments. Rising vessel traffic density and the resulting data overload from Automatic Identification System (AIS) records complicate real-time decision-making, often leading to overly conservative maneuvers or increased collision risks. To mitigate these issues, the authors propose a novel integrated approach that combines Belief-Rule-Based (BRB) reasoning with the Velocity Obstacle (VO) algorithm. The primary motivation is to reduce navigational complexity and decision dimensionality by grouping ships with similar movement trends, thereby enabling more efficient and safe avoidance strategies in multi-ship encounter scenarios. The methodology begins with the temporal alignment of asynchronous AIS dynamic data, including position, course over ground, and speed over ground, using linear interpolation to ensure a consistent time base. The BRB framework then clusters ships based on five specific metrics: spatial distance, speed difference, course difference, average speed, and course bearing angle. This reasoning process utilizes belief rules and evidential reasoning to group vessels with similar navigation trends and close proximity, effectively reducing the number of avoidance targets. Following clustering, the safety domain radius for individual ships and groups is determined proportionally to their length. Finally, the VO algorithm generates collision-free velocity vectors and feasible avoidance trajectories for the Own Ship, accounting for the defined safety domains and maritime constraints. The proposed method was validated through simulation experiments in two distinct scenarios. The results demonstrated that the integrated BRB-VO approach improves both navigational safety and operational efficiency in congested waters. By grouping ships rather than treating each vessel as an independent target, the system prevents the generation of overly conservative paths that often plague traditional methods in dense traffic. The computational load remains manageable as it scales linearly with the number of effective neighbors within a local interaction radius, rather than the total number of ships in the area. The significance of this work lies in its contribution to intelligent maritime traffic management and sustainable shipping development. By integrating situational awareness (via BRB grouping) with collision avoidance (via VO path planning), the study offers a robust, adaptive framework that enhances decision-making in dynamic environments. This approach addresses key research gaps regarding data overload and the fragmentation of traffic perception and avoidance decision-making, providing a foundation for future intelligent systems in maritime safety.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• time to collision looming