基于改进粒子群优化算法的无人水面艇动态避碰方法

Dynamic collision avoidance method for unmanned surface vehicle based on improved particle swarm optimization algorithm

针对"蓝信"号无人水面艇的动态避碰问题,提出一种基于改进粒子群优化算法的动态避碰方法.首先,考虑障碍物轮廓的长宽比不同,将障碍物膨化为圆形和椭圆形,并采用速度障碍原理求取避碰模型,同时,在避碰过程中加入国际海上避碰规则约束;其次,对粒子群优化算法进行自适应改进,使其针对避碰策略的求取能够快速收敛到最优解,提高算法的收敛速度与精度,满足避碰算法的快速性要求;最后,搭建虚拟视景仿真平台,模拟航行中的海洋环境,以"蓝信"号无人水面艇为模拟对象,对所提出的避碰算法进行仿真验证.仿真结果表明了该避碰方法的可行性和有效性,为无人水面艇的自主动态避碰提供了一种可行和有效的解决途径.

A dynamic collision avoidance method based on the improved particle swarm optimization(PSO)algorithm was proposed for the dynamic collision avoidance problem of"LanXin"unmanned surface vehicle.Firstly,as the different aspect ratio of obstacle contour,the obstacle was expanded into a circle and an ellipse to acquire the collision avoidance model by using the principle of velocity obstacle.At the same time,the international rules of collision avoidance were added in the process of collision avoidance.Secondly,the PSO algorithm was improved adaptively,so that the calculation of collision avoidance strategy can quickly converge to the optimal solution,and improved the convergence speed and accuracy of algorithm for satisfying the rapid requirements of the collision avoidance algorithm.Finally,a virtual visual simulation platform was built to simulate the marine environment in navigation,and taking the"LanXin"unmanned surface vehicle as the simulated object to verify the efficiency of the proposed avoidance algorithms.The simulation results show the feasibility and effectiveness of the proposed collision avoidance method,which provide a feasible and effective solution for the autonomous dynamic collision avoidance of unmanned surface vehicle.