Cooperative confrontation decision-making method and system for unmanned aerial vehicle swarm
A decision-making method and UAV technology, applied in control/regulation systems, instruments, three-dimensional position/channel control, etc., can solve the problem of single UAVs not considering high-value targets on the ground, and improve the level of cooperative confrontation, The effect of increasing attack effectiveness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0103] Such as figure 1 As shown, a UAV swarm cooperative confrontation decision-making method, including:
[0104] Step 1: Establish a three-dimensional battlefield environment containing high-value targets on the ground;
[0105] Step 2: Establish the motion model of the UAV;
[0106] Step 3: Establish the attack model of the UAV;
[0107] Step 4: Find the optimal strategy set for each UAV (UAV, Unmanned Aerial Vehicle);
[0108] Step 5: Establish a dynamic game model;
[0109] Step 6: In the optimal strategy set, determine the optimal response strategy of the UAV according to the dynamic game model.
[0110] Preferably in this embodiment, step 1: establish a three-dimensional battlefield environment containing high-value targets on the ground, including: setting the spatial coordinate system of the three-dimensional battlefield, the spatial range of the battlefield, the number of unmanned aerial vehicles, HVT related information, unmanned aerial vehicles Parameters such ...
Embodiment 2
[0178] The difference from Example 1 is that, as Figure 8 As shown, preferably in the present embodiment, in step 4, utilize genetic algorithm (GA, Genetic Algorithm) to find out the optimal strategy set of each unmanned aerial vehicle, promptly for each in the unmanned aerial vehicle bee colony All UAVs execute GA to obtain the optimal strategy set of each UAV. For UAVs numbered i (i=1, 2, 3, ..., n, n is the swarm of UAVs of one’s own side the total number of drones), including:
[0179] Step 421: Obtain battlefield situation information;
[0180] Step 422: Generate an initialization population;
[0181] Step 423: Calculate fitness;
[0182] Step 424: According to fitness, use roulette rules to select parents;
[0183] Step 425: Parents generate offspring through crossover and mutation;
[0184] Step 426: Calculate the fitness of the offspring;
[0185] Step 427: replace individuals with low fitness with offspring to form a new population;
[0186] Step 428: If the n...
Embodiment 3
[0192] The difference from Example 1 is that, as Figure 9 As shown, preferably in the present embodiment, in step 4, use differential evolution (DE, Differential Evolution) algorithm to find out the optimal policy set of each drone, that is, for each drone colony All UAVs execute the DE algorithm to obtain the optimal strategy set of each UAV. For the UAV numbered i (i=1, 2, 3, ..., n, n is its own UAV total number of drones in the swarm), such as Figure 9 shown, including:
[0193] Step 431: Initialization, including initialization of population size, individual dimension, and maximum number of iterations;
[0194] Step 432: Calculate the fitness of each individual
[0195] Step 433: mutation operation;
[0196] Step 434: cross operation;
[0197] Step 435: select an operation;
[0198] Step 436: Terminate the iteration after the number of iterations reaches the maximum number of iterations, otherwise, go to step 432 after the number of iterations is increased by on...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


