基于改进乌鸦搜索算法的无人艇新型路径规划策略

鉴于无人艇的实际航行需求，所规划的路径应满足顺滑性和经济性要求，为此提出一种基于改进乌鸦搜索算法和新型路径拟合方法的路径规划策略。文中提出一种新型路径拟合方法，用于优化转向点的数量并对转向点进行圆弧过渡处理，从而缩短路径长度，并保证无人艇在航速稳定的情况下实现转向，在此基础上提出一种改进的乌鸦搜索算法，用于优化路径转向点的位置。算法的改进主要体现在3个方面：采用反向学习策略以提高初始种群质量及多样性；提出一种动态变化的意识概率以提高算法局部和全局的搜索能力；采用莱维飞行策略以改善搜索的方向性和有效性。仿真结果表明，所提出的新型路径拟合方法优于B样条曲线拟合方法和直线段拟合方法。迭代计算和方差分析结果表明：在优化新型拟合路径方面，所提出的改进乌鸦搜索算法相较于标准乌鸦搜索算法、差分进化算法和遗传算法具有更高的收敛精度和鲁棒性，能更高效地处理无人艇路径规划的实际问题。

A new path planning strategy for unmanned surface vehicle based on improved crow searching algorithm

Becaused of the actual navigation requirements of unmanned surface vehicles, the planned path should meet the criteria of smoothness and economy. Therefore, a novel path planning strategy based on an improved crow search algorithm combining straight lines and circular arc turns is proposed. A new path fitting method is introduced to optimize the number of turning points and address the issue of arc transition at turning points. This method overcomes the problem of frequent direction adjustments caused by B-spline curve paths for unmanned surface vehicles, while ensuring that they can achieve steering while maintaining a stable speed, thereby improving navigation stability and economy. Based on this, an improved crow search algorithm is introduced to optimize the location of path turning points. The improvement of the algorithm is mainly reflected in three aspects: the use of a reverse learning strategy to optimize the quality and the diversity of the initial population, the proposal of a dynamically changing awareness probability to improve the global search ability of the initial segment and the local search ability of the final segment of the algorithm, and the utilization of the Levy flight strategy to improve the directionality and the effectiveness of the search. The simulation results show that the proposed new path fitting method is superior to the B-spline curve fitting method and the straight line segment fitting method. Building on this fitting method, the improved crow search algorithm, the standard crow search algorithm, the differential evolution algorithm, and the genetic algorithm are used to optimize the location of the path turning point. Iterative calculation and variance analysis results demonstrate that the proposed improved crow search algorithm exhibits higher convergence accuracy and robustness compared to the other three algorithms, effectively addressing practical problems in unmanned surface vehicle path planning.