COLLISION RISK ASSESSMENT MODEL FOR AUTONOMOUS SURFACE VESSELS CONSIDERING ENVIRONMENTAL INFLUENCES
https://doi.org/10.33815/2313-4763.2026.1.32.058-070
Abstract
The article is devoted to the development of a fuzzy logic-based model for assessing the collision risk of autonomous surface vessels under conditions of environmental uncertainty. The current state of development of collision avoidance systems for autonomous vessels is considered, and the key challenges associated with the processing of incomplete and imprecise navigational data are identified. A comparative analysis of existing approaches to collision risk assessment is carried out, in particular methods based on the distance and time to the closest point of approach (DCPA/TCPA) and fuzzy logic, with their advantages and limitations determined. A conceptual fuzzy logic-based model for ship collision risk assessment is proposed, providing a comprehensive evaluation of the risk level by taking into account the geometric parameters of the encounter area, the influence of environmental factors, and the uncertainty index of navigational information. A distinctive feature of the proposed model is the separation of geometric and contextual risk components, as well as the use of a two-layer fuzzy inference system that takes into account the constraints of COLREGs-72. It is shown that the integration of fuzzy logic methods, multi-criteria analysis, and new approaches to modeling environmental uncertainty can improve the reliability of risk assessment under real operating conditions of autonomous vessels. The structure of the developed risk assessment system is presented, its operation is demonstrated using typical ship encounter scenarios, and the degree of influence of external factors, including wind, current, and sea state, on the formation of the risk level is determined. Directions for further research are identified, in particular the use of fuzzy systems and evidence theory methods to account for the uncertainty of environmental factors affecting the motion control of autonomous vessels.
References
2. Burmeister, H.-C., Constapel, M. (2021). Autonomous Collision Avoidance at Sea: A Survey. Frontiers in Robotics and AI. 2021;8:739013. https://doi.org/10.3389/frobt.2021.739013.
3. Sarhadi, P., Naeem, W., Athanasopoulos, N. (2022). A Survey of Recent Machine Learning Solutions for Ship Collision Avoidance and Mission Planning. IFAC-PapersOnLine. 2022;55(31):257–268. https://doi.org/10.1016/j.ifacol.2022.10.440.
4. Zhu, Q., Xi, Y., Weng, J., Han, B., Hu, S., Ge, Y.-E. (2024). Intelligent ship collision avoidance in maritime field: A bibliometric and systematic review. Expert Systems with Applications. 2024;252(Part A):124148. https://doi.org/10.1016/j.eswa.2024.124148.
5. Yu, Q., Teixeira, A. P., Liu, K., Guedes Soares, C. (2022). Framework and application of multi-criteria ship collision risk assessment. Ocean Engineering. 2022;250:111006. https://doi.org/10.1016/j.oceaneng.2022.111006.
6. Ahmed, Y. A., et al. (2021). COLREGs Compliant Fuzzy-Based Collision Avoidance System for Multiple Ship Encounters. Journal of Marine Science and Engineering. 2021;9(8):790. https://doi.org/10.3390/jmse9080790.
7. Korupoju, A. K., Kapadia, V., Vilwathilakam, A. S., Samanta, A. (2025). Ship Collision Risk Evaluation using AIS and weather data through fuzzy logic and deep learning. Ocean Engineering. 2025;318:120116. https://doi.org/10.1016/j.oceaneng.2024.120116.
8. Park, J. (2026). Estimation of Vessel Collision Risk Under Uncertainty Using Interval Type-2 Fuzzy Inference Systems and Dempster–Shafer Evidence Theory. Journal of Marine Science and Engineering. 2026;14(1):34. https://doi.org/10.3390/jmse14010034.
9. Zhou, Y., Daamen, W., Vellinga, T., Hoogendoorn, S. P. (2020). Impacts of wind and current on ship behavior in ports and waterways: A quantitative analysis based on AIS data. Ocean Engineering. 2020;213:107774. https://doi.org/10.1016/j.oceaneng.2020.107774.
10. Hansen, P. N., Enevoldsen, T. T., Papageorgiou, D., Blanke, M. (2022). Autonomous Navigation in Confined Waters – A COLREGs Rule 9 Compliant Framework. IFAC-PapersOnLine. 2022;55(31):222–228. https://doi.org/10.1016/j.ifacol.2022.10.435.
11. Sawada, R., Sato, K., Minami, M. (2024). Framework of safety evaluation and scenarios for automatic collision avoidance algorithm. Ocean Engineering. 2024;300:117506. https://doi.org/10.1016/j.oceaneng.2024.117506.
12. Shi, Z., Zhen, R., Liu, J. (2022). Fuzzy logic-based modeling method for regional multi-ship collision risk assessment considering impacts of ship crossing angle and navigational environment. Ocean Engineering. 2022;111847. https://doi.org/10.1016/j.oceaneng.2022.111847.
13. Zhao, L., Fu, X. (2021). A novel index for real-time ship collision risk assessment based on velocity obstacle considering dimension data from AIS. Ocean Engineering. 2021;240:109913. https://doi.org/10.1016/j.oceaneng.2021.109913.
14. Gai, X., Zhang, Q., Hu, Y., Wang, G. (2024). A Fuzzy Fusion Method for Multi-Ship Collision Avoidance Decision-Making with Merchant and Fishing Vessels. Journal of Marine Science and Engineering. 2024;12(10):1822. https://doi.org/10.3390/jmse12101822.
15. Szlapczynski, R., Szlapczynska, J. (2021). A ship domain-based model of collision risk for near-miss detection and Collision Alert Systems. Reliability Engineering & System Safety. 2021;214:107766. https://doi.org/10.1016/j.ress.2021.107766.
16. Cheng, K., et al. (2025). A novel fuzzy comprehensive evaluation method for ship collision risk. Ocean Engineering. 2025;332:121462. https://doi.org/10.1016/j.oceaneng. 2025.121462.
17. Yuan, X., Zhang, D., Zhang, J., Zhang, M., Guedes Soares, C. (2021). A novel real-time collision risk awareness method based on velocity obstacle considering uncertainties in ship dynamics. Ocean Engineering. 2021;220:108436. https://doi.org/10.1016/j.oceaneng.2020.108436.
18. https://github.com/lpelykhivskyi/mass-collision-risk-simulation.
