Research On UAV Track Planning Method Based On Improved Ant Colony Algorithm

Unmanned aerial vehicle(UAV)have gradually become an emerging air platform,which has played an important role in the construction of the national economy and modern operations because of its good economy and superior maneuverability,which can replace manned aircraft to perform dangerous and complex tasks,etc.Features.With the expansion of the application scope of drones,the autonomous flight and mission planning capabilities of the drones have gradually become the focus of research,and the quality of the trajectory is the key to the successful completion of the mission.This paper focuses on the research of UAV's track planning in two-dimensional and three-dimensional planes.In order to solve the problem of UAV's track planning,an effective track planning algorithm is proposed,and the track optimization is performed.The main research contents of the full text are as follows:Based on the ant colony algorithm as the basic path planning algorithm,the ant colony algorithm was described in detail,and the advantages and disadvantages of the ant colony algorithm and its application range were analyzed.In view of the long search time of ant colony algorithm and easy to fall into local optimum,an adaptive polymorphic ant colony algorithm was proposed.Based on the polymorphic ant colony algorithm,adaptive parallel rules and pseudo-random rules were introduced.Ants implement state transfer based on pseudo-random rules.The optimal combination of state transition functions is obtained by adaptive parallel strategy.By adaptively updating the pheromone,the next node transition probability is adaptively updated.Parallel rules are introduced to implement global and local search,reducing search time,and strong global planning capabilities.Aiming at the complex three-dimensional environment with high impact,a fusion algorithm using artificial potential field method and ant colony algorithm was proposed.The artificial potential field method has a good local planning effect,and the ant colony algorithm has a good global planning effect.The fusion of the two algorithms achieves the complementary advantages of the algorithm and gives full play to the advantages of the fusion algorithm with strong applicability.Aiming at the problems of local minima and unreachable targets in the artificial potential field method,the repulsive force function in the repulsive force field was improved.The limit force was introduced to solve theproblem of local minima.The fusion of improved artificial potential field method and adaptive polymorphic ant colony algorithm was completed.The combined force of the improved artificial potential field method is applied to the heuristic function of the ant colony algorithm,and the potential field force is used to guide the ant colony algorithm to improve the initial optimization effect.Limiting factors were added,which limited the guiding effect of the artificial potential field method on the ant colony in the later stage and avoided the problem of local optimization due to the strong local planning effect.The two-dimensional plane was digitally processed using the grid method to construct a two-dimensional planning plane.The three-dimensional environment model is processed by two-dimensional cubic convolution interpolation to construct a three-dimensional planning space,which makes the three-dimensional model more consistent with the actual flight environment and improves the accuracy of track planning.The simulation analysis of the improved adaptive ant colony algorithm in a two-dimensional plane was completed.the simulation results fully verify the effectiveness of the algorithm.The trajectory planning of the artificial potential field ant colony fusion algorithm in complex three-dimensional space is realized,and the applicability of the fusion algorithm is stronger than that of a single algorithm and the accuracy is higher.The three-dimensional uniform B-spline is used to optimize the initial trajectory of a complex three-dimensional space plan.The optimized trajectory is smooth,the comprehensive cost is low,the actual flightability is high,and the accuracy is higher,which meets the maneuverability constraints of the UAV.