Track programming method used in searching of uncertain environment using multi unmanned aerial vehicles

Abstract

The invention provides a track programming method used in searching of uncertain environment using multi unmanned aerial vehicles. The track programming method comprises following steps: modeling of aflight environment is carried out, modeling of flight states is carried out, coding of genetic algorithm is carried out, and modeling of a searching probability graph is carried out; initialization of calculating parameters of the genetic algorithm is carried out; unmanned aerial vehicle flight mode is determined; the genetic algorithm is adopted for random generation of path population, the population with the largest reward is selected, the unmanned aerial vehicles are controlled to fly to the population, prediction of path at current positions is carried out, and the step is repeated; flymechanics are added into unmanned aerial vehicle flight environment; the unmanned aerial vehicle searching environment is divided into 9 zones, the distance between each pair of zones is designed to be the distance from the center of each zone to the center of another zone, and the distance between two zone sharing a same edge is defined to be 1, and the reward between each pair of zones is designed to be the reciprocal of the corresponding distance. The track programming method is capable of performing target search effectively, and enlarging map covering rate, realizing effective cooperationof a plurality of unmanned aerial vehicles, and increasing research efficiency.

Description

technical field [0001] The invention relates to the technical field of UAV track planning, in particular to a track planning method for searching uncertain environments by multiple UAVs. Background technique [0002] UAV path planning technology has developed rapidly in recent years. In the military and civilian fields, multi-UAV (Unmanned Aerial Vehicle, unmanned aircraft) technology is more and more applied to the task of cooperative target search, such as Use multiple drones to coordinate target search, post-disaster search and rescue, and coordinate transportation of goods. When planning the UAV path, the UAV may be interfered by various obstacles or no-fly zones, so that the UAV cannot search for as many targets as possible or the coverage of the UAV on the map is too low. These are not up to the task index of the map search. With the changes of the times and the advancement of technology, the path planning of drones needs to be more in-depth. [0003] For UAV path p...

AI Technical Summary

Problems solved by technology

In the invention patent with the application number 201610012608.5, PSO is used to plan the path of multiple UAVs. Compared with the genetic algorithm, it retains the population-based global search strategy and does not require crossover and mutation of GA, thereby avoiding complex genetic operations; However, in the case of convergence, since all the particles are flying towards the optimal solution, the particles tend to be identical (diversity is lost), which makes the later convergence speed significantly slower, so that the algorithm cannot continue when it converges to a certain accuracy. optimization

In the invention patent application with the application number 201610898192.1, the mobile patrol and round-up method is used to make each UAV move toward the center of the search area in a spiral direction according to the preset patrol route. This method enables the UAV to search as much as possible in an uncertain environment. There are many targets, but this method takes a long time, and the track of UAV may be repeated, resulting in a certain waste of resources

Images