We propose multi-objective social learning pigeon-inspired optimization (MSLPIO) and apply it to obstacle avoidance for unmanned aerial vehicle (UAV) formation. In the algorithm, each pigeon learns from the better pigeon but not necessarily the global best one in the update process. A social learning factor is added to the map and compass operator and the landmark operator. In addition, a dimension-dependent parameter setting method is adopted to improve the blindness of parameter setting. We simulate the flight process of five UAVs in a complex obstacle environment. Results verify the effectiveness of the proposed method. MSLPIO has better convergence performance compared with the improved multi-objective pigeon-inspired optimization and the improved non-dominated sorting genetic algorithm.

我们提出了多目标社会学习鸽子启发式优化（MSLPIO），并将其应用于避开无人机的无人机。在算法中，每羽鸽子都从更好的鸽子那里学习，但不一定要在更新过程中向全球最好的鸽子学习。将社交学习因素添加到地图和罗盘操作员以及地标操作员。另外，采用基于尺寸的参数设置方法来提高参数设置的盲目性。我们在复杂的障碍环境中模拟五架无人机的飞行过程。结果验证了所提方法的有效性。与改进的多目标鸽子启发式优化和改进的非支配排序遗传算法相比，MSLPIO具有更好的收敛性能。