研究船舶碰撞危险度的目的是为避碰决策提供依据。
The purpose of studying vessel collision risk index is to provide a scientific basis for decision-making aimed at avoiding vessel collision.
根据多船会遇避碰决策的特点，提出了基于层次分析方法的多船避碰模型。
According to features of multi ship collision avoidance decision making, a model of multi ship collision avoidance based on the AHP method is presented in the paper.
基于前述研究提出了基于AIS信息的避碰决策辅助分析系统的解决方案。
Because of the further research the solving scheme for the assistance analysis system of vessel collision avoidance decision based on AIS has been put forward.
利用AIS数据作为辅助船舶避碰决策系统的环境信息来源是本论文的出发点。
It was the paper's staring point that using AIS data as environment information sources of the assistance decision system of Collision Avoidance.
最后以模块化思想为主线将评估系统软件分为计算模块、避碰决策模块、评估模块和数据库管理模块四个部分。
According to modularization, the main system software is divided into four parts: calculation module, decision-making in avoiding collision module, evaluation module and database module.
针对船舶避碰决策系统中的船舶运动趋势和避碰时机建立数学模型，实时预估目标船相对于本船的最近会遇距离和最近会遇时间。
Aiming at shipping movement and the time of collision avoidance in decision-making collision avoidance, a mathematical model was used for ship collision avoidance and to forecast the DCPA and TCPA.
值得指出的是，本软件在给出了避碰方案、行动时机、转向幅度与复航时间的基础上，实现了多船会遇船舶避碰决策的自动仿真。
It should be noted that this software can give out the project, the opportune moment, the extent of veer and the reversion of course, complete the auto-simulation of Multi-ship Collision Avoidance.
该研究对于完善碰撞危险度的内涵，建立碰撞危险度模型，及在建立自动避碰决策系统中的应用，具有重要的理论和实际应用价值。
The research has an important value to improve the connotation of SCR, establishment of the model and the establishment of automatic decision making system of collision avoidance.
主要采用强化学习的方法对AUV进行控制和决策，综合Q学习算法、BP神经网络和人工势场法对AUV进行避碰规划。
The reinforcement learning is adopted to control and decision for AUV, and Q-learning, BP neural net, artificial potential is integrated to avoidance planning for AUV.
主要采用强化学习的方法对AUV进行控制和决策，综合Q学习算法、BP神经网络和人工势场法对AUV进行避碰规划。
The reinforcement learning is adopted to control and decision for AUV, and Q-learning, BP neural net, artificial potential is integrated to avoidance planning for AUV.
应用推荐