Improved chaos ant colony algorithm-based unmanned aerial vehicle airway planning method

Abstract

The invention discloses an improved chaos ant colony algorithm-based unmanned aerial vehicle airway planning method. The method comprises the following steps: 1, converting an optimized solution obtained by a chaos optimization algorithm into a pheromone initial value of an ant colony algorithm; and 2, performing airway optimization through the ant colony algorithm, and performing chaotic mappingon the eligible airway after the optimization ends to obtain an optimal airway. The pheromone initial value of every ant difference, generated by using chaotic mapping substitutes the same pheromone initial value of original ants in order to generate an ant colony algorithm-based new initial airway, so the searching efficiency of the algorithm is improved; and a chaotic disturbance pheromone update strategy is introduced to dynamically update the pheromone with the obtained effective airway, so local optimal defects are effectively overcome, and the convergence speed is improved.

Description

technical field [0001] The invention relates to the technical field of UAV route planning, in particular to an UAV route planning method based on an improved chaotic ant colony algorithm. Background technique [0002] UAV route planning refers to finding the optimal or feasible route for UAVs from the starting position to the target position and satisfying given constraints and performance indicators within a given planning space. Constraint conditions mean that the planned route must meet constraints such as the UAV's own maneuverability constraints, the space-time constraints of the flight space, and the total amount of fuel carried by the aircraft. The selection of performance indicators depends on the specific research object and task requirements, or make it the highest task efficiency, or maximize the probability of survival, or the shortest flight time, or arrive at the specified time, or the least cost, or high real-time performance. [0003] The trajectory planning...

AI Technical Summary

Problems solved by technology

However, the disadvantage of the Voronoi diagram is that it is only suitable for single aircraft route planning, and has no planning ability in the battlefield environment with dynamic threats, and cannot meet the operational needs of modern battlefields; the A* algorithm is a typical deterministic search algorithm, which requires Construct a heuristic function, however, the constructed heuristic function directly determines the operational efficiency of the A* algorithm, and due to the existence of various uncertain factors in the planning space, it is impossible to construct a heuristic function that accurately reflects the flight threat, so in complex flight constraints Planning failures are prone to occur in the environment; Ant Colony Algorithm (ACO) is also a typical bionic algorithm, which simulates the foraging process of ants in the insect kingdom. Pheromone is left on the passing route, and the ants that arrive later will guide their travel based on the pheromone remaining on the route, and eventually all ants tend to choose the same route for foraging

However, when the number of ants is large, it is difficult to find the optimal route among a large number of chaotic routes in a short period of time, and the convergence process of the algorithm is relatively slow; and due to the existence of the positive feedback characteristics of the algorithm, it may cause local routes. Excessive accumulation of pheromones, these pheromones with too high concentration will affect the selection of routes by ants arriving later, and will cause a large number of ants to choose a certain route, which will eventually lead to the stagnation of the algorithm. In order to improve the convergence speed of the algorithm and global search Excellent ability, the improved chaos mechanism can be added to the basic ant colony algorithm

Images