Design and Research of Ship Collision Avoidance Simulation System Based on Artificial Intelligence

Wang, Guozheng; Wang, Yi; Deng, Hua

doi:10.1007/978-981-16-0115-6_119

Cited by 1 publication

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it has limitations in dealing with collision avoidance among inland ships, and it is also unable to deal with collision avoidance in close-quarters situations. At the same time, there are new intelligent algorithms based on artificial intelligence [14], data processing [15], and scene prediction [16]. However, the collision-avoidance algorithm suitable for inland rivers remains to be studied.…”

Section: Introductionmentioning

confidence: 99%

Collision-Avoidance Decision System for Inland Ships Based on Velocity Obstacle Algorithms

Zhang

Wang

Liu³

et al. 2022

JMSE

View full text Add to dashboard Cite

Due to the complex hydrology and narrow channels of inland rivers, ship collision accidents occur frequently. The traditional collision-avoidance algorithms are often aimed at sea areas, and not often at inland rivers. To solve the problem of inland-ship collision avoidance, this paper proposes an inland-ship collision-avoidance decision system based on the velocity obstacle algorithm. The system is designed to assist ships in achieving independent collision-avoidance operations under the limitation of maneuverability while meeting inland-ship collision-avoidance regulations. First, the paper improves the Maneuvering Modeling Group (MMG) model suitable for inland rivers. Then, it improves velocity obstacle algorithms based on the dynamic ship domain, which can deal with different obstacles and three encounter situations (head-on, crossing, and overtaking situations). In addition, this paper proposes a method to deal with close-quarters situations. Finally, the simulation environment built by MATLAB software is used to simulate the collision avoidance of inland ships against different obstacles under different situations with a decision-making time of less than 0.1 s. Through the analysis of the simulation results, the effectiveness and practicability of the system are verified, which can provide reasonable collision-avoidance decisions for inland ships.

show abstract

Section: Introductionmentioning

confidence: 99%