To address the dynamic autonomous collision avoidance problem of ships in coastal waters, this paper proposes an autonomous collision avoidance model by combining the trajectory prediction with the improved velocity obstacle model. Firstly, the relative motion model of the two ships is established and the motion parameters of collision avoidance are calculated in real time. Based on the three-degree-of-freedom Maneuvering Modelling Group (MMG in short) model and dead reckoning algorithm, the motion state of the own ship (OS in short) and the target ships (TS in short) at the next moment will be predicted, respectively. Then dynamic autonomous collision avoidance decision-making model is designed with the combination of "International Regulations for Preventing Collisions at Sea” (COLREGs in short), good seamanship, trajectory prediction model, improved velocity obstacle algorithm, and course control system. Finally, the feasibility and validity of the dynamic autonomous collision avoidance decision-making model are verified through simulation experiments. The simulation results show that the model can realize the autonomous collision avoidance in different typical encounter situations, allowing the safe navigation of ships under dynamic collision avoidance conditions.
Ship dynamic autonomous collision avoidance model based on improved velocity obstacle
International Conference on Mechatronics and Intelligent Control (ICMIC 2024) ; 2024 ; Wuhan, China
Proc. SPIE ; 13447
16.01.2025
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DOAJ | 2022
|Ship Collision Avoidance Autonomous Avoidance System using Deep Learning
Europäisches Patentamt | 2021
|