Application of uniform experimental design theory to multi-strategy improved sparrow search algorithm for UAV path planning

The sparrow search algorithm (SSA) is a meta-heuristic optimization algorithm based on the predatory behavior of sparrows. However, SSA tends to fall into the local optimum when solving optimization problems with complex constraints. To improve its optimization efficiency and overall performance, this paper develops a multi-strategy improved SSA (ISSA) based on uniform experimental design theory. Specifically, the wraparound L2-discrepancy (WD), as a uniformity metric for uniform design of experiments, is fully utilized with macro-regulation, adaptive dynamic management strategy, and boundary redistribution management mechanism to quantify the population uniformity in each iteration of ISSA. Inspired by the concept of uniform design, WD is initially adopted to gauge population uniformity, and the threshold acceptance (TA) algorithm is employed to produce an initial population with improved uniformity, hence augmenting the population's diversity and quickening the rate of convergence. Secondly, a macroscopical individual iterative strategy of the producer is adjusted to avoid the population converging to the origin. Then, a dynamic population uniformity affiliation function based on WD is introduced to adjust the population uniformity affiliation function according to the relative amount of change in the global optimum, and the number of danger perceivers is adjusted according to the affiliation function. What is more, a new boundary update strategy is also proposed in ISSA based on population uniformity. By comparing ISSA on 23 standard test functions and recently updated validation function set CEC2022 with the original SSA, and some classical as well as newly developed algorithms, the superiority of the present ISSA is thoroughly confirmed. As an application case, the ISSA algorithm is utilized to solve the path planning problem of the complex environment of unmanned aerial vehicle (UAV) based on threat models by applying it to 2D maps containing circular and polygonal obstacles, as well as 3D maps containing mountain peaks and cylindrical obstacles. The simulation results show that ISSA can find more effective routes through various environments with obstacles.