The invention relates to a ship collision avoidance method, and belongs to the technical field of ship navigation, and the method comprises the steps: determining a first collision avoidance behavior based on a fully trained deep learning model; determining a second collision avoidance behavior based on the constructed ship collision avoidance mechanism model; constructing a discriminator based on the coincidence degree of the collision avoidance behavior and the crew avoidance behavior preference and the collision risk change degree; and selecting an optimal collision avoidance behavior from the first collision avoidance behavior and the second collision avoidance behavior based on the discriminator. According to the invention, by introducing a deep learning and discrimination mechanism, a data-mechanism fused ship collision avoidance behavior model is established, and the conformity of a collision avoidance decision and navigation practice is improved.
本申请涉及一种船舶避碰方法,属于船舶航行技术领域,其中,该方法包括:基于训练完备的深度学习模型确定第一避碰行为;基于构建的船舶避碰机理模型确定第二避碰行为;基于避碰行为与船员避让行为偏好的符合程度和碰撞风险变化程度,构建判别器;基于所述判别器从所述第一避碰行为和所述第二避碰行为中选取最优避碰行为。本申请通过引入深度学习和判别机制,建立数据‑机理融合的船舶避碰行为模型,提升了避碰决策与航海实践的符合性。
Ship collision avoidance method
一种船舶避碰方法
11.02.2025
Patent
Elektronische Ressource
Chinesisch
Europäisches Patentamt | 2023
|