基于精英族系遗传算法的AUV集群路径规划

针对传统路径规划算法仅能规划单一最短路径且不能调节路径宽度而难以适用于自主式水下航行器(autonomous underwater vehicle, AUV)集群航路规划的缺陷, 提出了精英族系遗传算法(elite family genetic algorithm, EFGA)。该算法将基因适应度加入适应度评价函数中, 同时在进化过程中标记精英个体作为多路径规划结果, 并在该算法基础上针对AUV集群路径规划问题设计了一种多智能体路径规划(multi-agent path planning, MAPP)方法。仿真结果表明, 该算法可以求解无冲突路径集合实现MAPP, 通过实现AUV集群的最优多路径航行方案减少集群的航行耗时, 且能够满足不同AUV编队规模对可调路径宽度的需求。

AUV swarm path planning based on elite family genetic algorithm

Aiming at the defect that the traditional path planning algorithm can only plan a single shortest path and can not adjust the path width, which is difficult to apply to the cluster route planning of autonomous underwater vehicle (AUV), a genetic algorithm based on elite family (EFGA) is proposed. In this algorithm, gene fitness is added to the fitness evaluation function, and elite individuals are marked as the result of multi-path planning in the process of evolution. Based on this algorithm, a multi-agent path planning (MAPP) method is designed for AUV cluster path planning. Simulation results show that the algorithm can solve the conflict free path set, realize MAPP, reduce the navigation time of underwater vehicle cluster by realizing the optimal multi-path navigation scheme of AUV cluster, and meet the requirements of adjustable path width for different AUV formation sizes.