A multi-strategy particle swarm algorithm with exponential noise and fitness-distance balance method for low-altitude penetration in secure space

UAV technology is at the forefront of current research and plays an important role in agriculture, public safety and the military. Low altitude trajectory is a technology for UAVs to fly safely in situations full of various threats, so the safety and stability of the flight path is an important challenge. Current swarm intelligence (SI) algorithms are widely used in path planning problems due to their high robustness and global search capability, but most of them do not take into account the universality of such problems and flight control in safe space, so it is particularly important to improve the ability of SI to plan paths in multiple environments. To better improve the competitiveness of SI in such problems, this paper proposes a multi-strategy particle swarm algorithm based on exponential noise to solve low altitude penetration in secure space, and the algorithm is abbreviated as MEPSO. A selective opposition (SO) strategy is introduced in the traditional particle swarm algorithm to dynamically update the position of individuals and improve the flexibility of the algorithm; then uses exponential noise and fitness-distance balance (FDB) to expand the search space and prevent the algorithm from falling into a local optimum, further enhance the optimization capability of the algorithm. Comparing MEPSO with 4 basic algorithms and 7 variants of other algorithms, the results show that the minimum and mean costs of MEPSO in simple environments are 72.5850 and 72.7472, respectively. It also shows that the minimum and mean cost in complex environments are 73.2984 and 73.3312, respectively. MEPSO has better global optimization capability than other algorithms. The safety and stability of the paths in both environments are high, which verifies that the path planning capability of MEPSO is reasonable and effective in the low altitude penetration in secure space.