An IPSO-SA algorithm based on feedback mechanism for smooth path planning of UAV

Abstract

Abstract The traditional PSO algorithm has been widely used in the path planning of unmanned equipment, but its algorithm is faced with the problem of premature convergence, which is easy to fall into the local optimal solution. When the initial position is not suitable, it can’t even plan the path in complex environment. At the same time, its line trajectory does not meet the requirements of the path curvature of realistic unmanned equipment. To solve the above problems, this paper proposes a new path planning strategy for unmanned equipment, and designs a new path planning algorithm for unmanned aircraft by combining the improved particle swarm optimization (IPSO) algorithm with simulated annealing algorithm (SA). At the same time, it solves the two problems that PSO algorithm is easy to fall into local optimal solution and abandoning all possible feasible solution regions in the early stage because of an illegal path. The path planned by IPSO-SA algorithm is processed by cubic spline interpolation to solve the curvature problem of its motion path. In addition, in view of the problem that the initial point is not suitable in complex environment, this algorithm designs a feedback mechanism to correct the initial point in time. The effectiveness of the algorithm is verified by theoretical derivation and simulation experiments, that is, the algorithm only needs a small number of point sequences to plan the path of UAV in simple and complex environment, and has less search amount and space-time overhead.