A novel hybrid particle swarm optimization for multi-UAV cooperate path planning

The path planning of unmanned aerial vehicle (UAV) in three-dimensional (3D) environment is an important part of the entire UAV's autonomous control system. In the constrained mission environment, planning optimal paths for multiple UAVs is a challenging problem. To solve this problem, the time stamp segmentation (TSS) model is adopted to simplify the handling of coordination cost of UAVs, and then a novel hybrid algorithm called HIPSO-MSOS is proposed by combining improved particle swarm optimization (IPSO) and modified symbiotic organisms search (MSOS). The exploration and exploitation abilities are combined efficiently, which brings good performance to the proposed algorithm. The cubic B-spline curve is used to smooth the generated path so that the planned path is flyable for UAV. To assess performance, the simulation is carried out in the virtual three-dimensional complex terrain environment. The experimental results show that the HIPSO-MSOS algorithm can successfully generate feasible and effective paths for each UAV, and its performance is superior to the other five algorithms, namely PSO, Firefly, DE, MSOS and HSGWO-MSOS algorithms in terms of accuracy, convergence speed, stability and robustness. Moreover, HIPSO-MSOS performs better than other tested methods in multi-objective optimization problems. Thus, the HIPSO-MSOS algorithm is a feasible and reliable alternative for some difficult and practical problems.

Automated summary

The study introduces a novel approach for optimal path planning for multiple UAVs in complex environments using the HIPSO-MSOS algorithm, which combines different optimization strategies to enhance performance and reliability. Experimental results demonstrate the superior performance of the HIPSO-MSOS algorithm in multi-objective optimization problems, successfully generating effective paths.