Improved Sparrow Search Algorithm And Application For UAV Trajectory Planning

With the development of information technology,the UAV technology has been greatly enhanced and therefore has a wide range of applications in some fields,such as agricultural,industry and military.One of the key technologies for autonomous control system of UAV is route planning.The UAV needs to calculate an optimal collision-free route from the starting position to the ending position according to the mission requirements,while needing to meet the constraints of the external environment and the UAV’s own performance.The UAV route planning problem is a multi-constrained combinatorial optimization problem,the difficulty of which lies in the complex mathematical model,the many constraints involved,and the existence of many local optimal solutions,leading to the low quality of the route planned by traditional methods.Based on the research of UAV route planning problem and swarm intelligence algorithm,this thesis proposes a modified sparrow search algorithm to solve the complex UAV route planning problem.The main research contents and results of this thesis are as follows:(1)This thesis studies various constraints of the UAV route planning problem,including the requirements of obstacle avoidance,route length,flight altitude and turning angle,whose cost function models are then established.In order to make the experimental environment closer to the real flight environment,the mission environment is modeled based on digital elevation map data of real mountain terrain,and many barriers were modeled.To make the route meet the requirements of UAV,this thesis adopts B-spline method to smooth the route.(2)In order to solve the shortcomings of the original sparrow search algorithm,such as insufficient population diversity,insufficient balance between global search and local exploitation ability,and easy to fall into local optimum,a modified sparrow search algorithm is proposed in this thesis.Firstly,the chaotic strategy is introduced to enhance the diversity of the population of the algorithm.Secondly,the adaptive inertia weight is used to balance the convergence rate and exploration capabilities of the algorithm.Finally,the Cauchy-Gaussian mutation strategy is adopted to enhance the capability of the algorithm to get rid of stagnation.(3)In this thesis,three sets of experiments are designed to verify the performance of the modified sparrow search algorithm.The first set of experiments selected four test functions for visualization,showing the population distribution and search route of the algorithm.In the second set of experiments,eight single-peak test functions were selected to verify the search speed and convergence accuracy of the algorithm.The third set of experiments selected eight multi-peaked test functions for verifying the global search ability of the algorithm and the ability to jump out of the local optimum.The experimental results show that the modified sparrow search algorithm has obvious advantages in search speed,convergence accuracy and stability compared with the gray wolf optimization algorithm,particle swarm algorithm,whale optimization algorithm and the original sparrow search algorithm.(4)In this thesis,the modified sparrow search algorithm is used to solve the UAV route planning problem in two complex mission environments.The experimental results show that compared with the original sparrow search algorithm,the modified sparrow search algorithm is more efficient in solving the UAV route planning problem,and the route planned by the modified sparrow search algorithm has the advantages of length and smoothness.In summary,the acquired route of the modified sparrow search algorithm can meet the flight requirements of the UAV.