Cooperative Path Planning of Multi-unmanned Aerial Vehicle Based on Improved Pigeon Inspired Optimization

The trajectory planning problem can provide reference instructions for multiple unmanned aerial vehicles (UAVs) cooperative missions in complex environments. Current methodologies for calculating flight trajectories frequently encounter obstacles such as delayed convergence speed and a high probability of stagnating at suboptimal solutions. To overcome these inherent deficiencies, this study introduces an enhancement of the pigeon inspired optimization (PIO) framework, referred to as HPIO. The algorithm employs two primary strategies, an expansive optimization mechanism and an update strategy integrating historical iteration information, respectively. The expansive optimization mechanism introduces a random inertia weight factor to enhance the capability to perform global search and to escape local optima. The update strategy utilizes superior solutions from previous iterations to guide the early-stage search process, thereby accelerating convergence speed. Simulation results reveal that the HPIO method is superior to conventional approaches regarding path cost, planning success rate, and the speed of convergence.