基于多项式混沌展开的船舶避碰鲁棒轨迹规划  

Robust trajectory planning for ship collision avoidance based onpolynomial chaotic expansion

作　　者：祁新宇 张智[1] 尚晓兵 张艺琼 姜立超 周悦欣 QI Xinyu;ZHANG Zhi;SHANG Xiaobing;ZHANG Yiqiong;JIANG Lichao;ZHOU Yuexin(School of Intelligent Science and Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学智能科学与工程学院,黑龙江哈尔滨150001

出　　处：《系统工程与电子技术》2025年第2期621-632,共12页Systems Engineering and Electronics

基　　金：国家自然科学基金(62303129);黑龙江省自然科学基金(LH2023F022);中央高校基本科研业务费(3072024XX0404)资助课题。

摘　　要：现有的船舶避碰轨迹规划大部分是以精确的运动模型和环境信息为前提,难以应对实际环境中存在的多种不确定海况因素,并导致规划出的轨迹安全可靠性降低。针对以上问题,提出一种基于多项式混沌展开法的船舶鲁棒轨迹规划方法,将船舶水动力学模型中的水动力系数视为不确定性参数,以碰撞危险度及舵角控制量为目标函数,建立船舶轨迹规划的最优控制模型,并使用遗传算法求得控制量与优化后的轨迹。仿真实验结果表明,优化后的轨迹最小距离以及最大会遇距离均提升10%~20%,平均碰撞危险度降低10%,实验结果表明考虑不确定性的船舶轨迹规划更加安全可靠。Most of the existing ship collision avoidance trajectory planning is based on accurate motion mo-dels and environmental information,which makes it difficult to cope with various uncertain sea conditions in the actual environment and leads to a decrease in the safety and reliability of the planned trajectory.A robust trajectory planning method for ships based on polynomial chaotic expansion method is proposed to address the above issues.The hydrodynamic coefficients in the ship hydrodynamic model are considered as uncertain parameters,and the collision risk and rudder angle control variables are used as objective functions to establish the optimal control model for ship trajectory planning.Genetic algorithm is used to obtain the control variables and optimized trajectory.The experimental results show that the minimum distance and maximum encounter distance of the optimized trajectory are increased by 10%-20%,and the average collision risk is reduced by 10%.The experimental results prove that the ship trajectory considering uncertainty is more safer and reliable.

关 键 词：船舶避碰 多项式混沌展开 碰撞危险度 最优控制 遗传算法 

分 类 号：U675[交通运输工程—船舶及航道工程]