A decision-making method for large-scale UAV swarm dynamic confrontation

Abstract

The invention discloses a decision-making method for dynamic confrontation of large-scale UAV clusters. The steps are: each UAV conducts situational assessment according to the battlefield environment information, and aims at maximizing attack benefits, and realizes multi-machine coordination and multi-target allocation decision-making; Establish a swarm movement model based on social forces, and according to the target assignment results, each UAV selects the corresponding behavior rules to update its own speed and position; each UAV makes an attack decision, and judges whether the assigned target meets the attack conditions , if satisfied, then attack the target and update the number of weapons and the survival probability of the enemy target, otherwise judge whether the battle is over. The present invention performs target allocation and negotiation in real time through communication among drones, and establishes a cluster motion model to update the speed and position of the drones, thereby further realizing dynamic confrontation among clusters of drones.

Description

technical field [0001] The invention belongs to the technical field of air combat decision-making, and in particular relates to a decision-making method for large-scale unmanned aerial vehicle cluster dynamic confrontation. Background technique [0002] With the increasing complexity of the battlefield environment and the increasing diversification of combat missions, the combat style of UAVs is gradually developing from a single platform to a multi-platform "swarm" (Swarm). Using a large number of low-cost UAVs to form a cluster to carry out saturation strikes on important enemy targets will become the main combat style of UAV clusters. The most effective way to deal with drone swarm saturation attacks is to use drone swarms to intercept the invading fleet, which leads to aerial confrontation of drone swarms. In the process of cluster confrontation, the air combat situation is constantly changing, and each UAV must make real-time decisions according to the changing situati...

AI Technical Summary

Problems solved by technology

At present, the methods to solve the target allocation problem mainly include Ant Colony Algorithm (ACO), Particle Swarm Algorithm (PSO), Genetic Algorithm (GA), etc., but there are generally problems such as low efficiency and non-convergence, and are only suitable for static target allocation; For the movement decision-making of UAV clusters, the behavior control method based on bionic intelligence is usually adopted. By designing the individual behavior rules and control strategies of UAVs, large-scale UAVs with autonomous capabilities can interact to form an orderly system. Overall, but the swarm movement control strategy for specific combat tasks still needs further research

At present, for the UAV swarm confrontation problem, the main strategy is to decompose the many-to-many cluster air combat into one-to-one confrontation, but the multi-UAV air combat decision-making method is generally only suitable for small-scale UAV swarms. When the number of confrontation individuals is huge and the combat situation is constantly changing, it will be difficult for traditional air combat decision-making methods to solve the dynamic confrontation problem between large-scale UAV clusters.

Images