基于粒子群优化算法的USV集群协同避碰方法

USV cluster collision avoidance based on particle swarm optimization algorithm

针对无人水面艇(unmanned surface vessel,USV)集群在路径规划中的协同避碰问题,提出了基于滚动优化策略结合粒子群优化算法的USV集群协同避碰方法。首先,通过已有雷达、光电等传感器参数指标建立综合视域模型;其次,采取基于正切函数的惯性权重调整结合线性调整学习因子的方法来提高粒子群优化算法的全局搜索能力,同时,在适应度函数中加入转艏角控制来提高路径的平滑性;最后,利用改进后的粒子群优化算法规划出每个综合视域内的路径。仿真实验结果表明,该优化算法能实现USV集群的实时避碰,并快速为USV集群规划出平滑、安全的全局最优无避碰路径。

To deal with the collaborative collision avoidance problem in path planning for unmanned surface vessel (USV) clusters,a USV cluster coordination collision avoidance method based on the rolling optimization strategy and the particle swarm optimization algorithm is proposed.Firstly,a comprehensive field of the view model is established by existing sensor parameters such as radar and photoelectric.Secondly,the standard particle swarm optimization algorithm is easy to fall into the local optimal problem.The inertia weight adjustment based on the tangent function is combined with the linear adjustment learning factor to improve the global search ability of the particle swarm optimization algorithm.At the same time,the transition angle control strategy is added to the selection of the fitness function to improve the smoothness of the path.Finally,the improved particle swarm optimization algorithm is used to plan the path in each integrated view.The simulation results show that the optimization algorithm can realize real-time collision avoidance of USV clusters,and quickly plan a smooth and secure global optimal path for USV clusters.