Research On UAV Path Planning Technology

Unmanned aerial vehicle(UAV)has attracted the attention of military organizations all over the world because of its high mobility,excellent intelligence detection ability and fast processing ability in the harsh environment,but at the same time,the modern battlefield environment also puts forward higher requirements for UAV.When uavs fly at a fixed altitude in the air to perform combat missions,they need to be able to accurately avoid enemy threats such as radar,artillery and no-fly zones;When unmanned aerial vehicles(UAVs)perform tasks in locally unknown or completely unknown 3D environments,they need to be able to process a large amount of environmental information in real-time and make fast and effective online path planning.In order to obtain high-efficiency and high-precision UAV path planning results,and realize UAV online path planning in an unknown environment.On the basis of fully considering the flight environment constraints,mission requirements constraints and self-mobility constraints of UAV,this paper puts forward a two-dimensional path planning algorithm for UAV in a known environment and a three-dimensional online path planning algorithm for UAV in an unknown environment,thus providing technical support for UAV application in the actual environment.In this paper,firstly,the two-dimensional path planning problem of UAV in a known environment is analyzed,and an improved fast convergence artificial bee colony(FCABC)algorithm is proposed to solve the problem by introducing UAV physical constraints into the solution space.In the honey source initialization stage,the algorithm adopts random honey source initialization method based on UAV physical constraints,which ensures the diversity of population and the feasibility of initial track;In the neighborhood search stage of hired bees,a heuristic adaptive algorithm based on the combination of UAV physical constraints and optimal honey source information is adopted,and the bees are guided by the optimal honey source information to explore the neighborhood,which accelerates the convergence speed of the algorithm.When choosing the honey source for employment,the follower bees adopted a selection mechanism based on ε-Boltzmann exploration strategy and honey source location information to enhance the global search ability of the algorithm,which greatly reduced the possibility of the algorithm falling into a locally optimal solution.Simulation results show that the FCABC algorithm has a better solution effect than other improved artificial bee colony algorithms.To solve the problem of unmanned aerial vehicle(UAV)online path planning in a three-dimensional unknown environment,this paper innovatively combines the idea of spatial stratification with lazy theta* algorithm,and proposes an improved sparse layered lazy theta*(SHLT*)algorithm to solve this problem.The algorithm uses the sparse hierarchical framework to model three-dimensional space,divides the whole space into different levels of subspaces,and introduces UAV dynamics constraints to optimize successor nodes,thus greatly reducing the search space of the algorithm.On the basis of this framework,this paper adopts the adaptive lazy theta* algorithm to find the shortest path in all levels of space,speeding up the calculation of the algorithm and improving the quality of the generated path.Finally,the generated path is smoothed and polished to remove unnecessary turns and sharp corners in the path.Simulation results show that SHLT* algorithm can plan a path from the starting point to the end point in a short time,and can produce a shorter and smoother path compared with the hierarchical D*lite(HD*) algorithm.