Small unmanned aerial vehicle prevention and control hybrid decision-making method and system based on deep reinforcement learning and rule driving

Abstract

The invention discloses a small unmanned aerial vehicle prevention and control hybrid decision-making method and system based on deep reinforcement learning and rule driving, and the method comprises the steps: obtaining the position motion information of a small unmanned aerial vehicle, and constructing a three-degree-of-freedom particle motion model of the small unmanned aerial vehicle; constructing a small unmanned aerial vehicle prevention and control rule model, and describing small unmanned aerial vehicle prevention and control steps by using the small unmanned aerial vehicle prevention and control rule model and the three-degree-of-freedom particle motion model; constructing a state space S, an action space A and a reward function R according to a Markov decision process; establishing a D3QN network based on a dueling structure, and training and optimizing a prevention and control decision model; and updating the small unmanned aerial vehicle prevention and control rule model according to the prevention and control decision model. The small unmanned aerial vehicle prevention and control mixed decision model is constructed, the automation level of a small unmanned aerial vehicle prevention and control system for performing prevention and control tasks can be effectively improved, the problems that in existing small unmanned aerial vehicle prevention and control command decision, the decision speed is low, and complex scenes are difficult to process are solved, and the command decision requirement for preventing and controlling the small unmanned aerial vehicle is met.

Description

technical field [0001] The invention belongs to the technical field of command and control, and in particular relates to a mixed decision-making method and system for prevention and control of small UAVs based on deep reinforcement learning and rule-driven. Background technique [0002] With the rapid development and application of "low, slow and small" drones, it poses a great threat to the public safety and national security of all countries. In the civilian field, drones have seriously disrupted the order of air traffic control; in the military field, drones have become a new type of combat weapon, and have achieved good strike results in local conflicts. Therefore, countries around the world are speeding up the research on anti-UAV technology and means. Among them, command decision-making needs to coordinate and control multi-source detection and multi-disposal means to prevent and control targets and evaluate the prevention and control effect. It is the current anti-UAV...

AI Technical Summary

Problems solved by technology

However, the existing prevention and control systems have the following problems: (1) The environment for the prevention and control of small UAVs is complex, and the existing decision-making system and process are difficult to adapt to; (2) The decision-making time is short, and manual operation is slow and difficult to deal with Many goals

However, there are also some problems in the command decision-making based on deep reinforcement learning: (1) In practical problem scenarios such as the prevention and control of small UAVs, deep reinforcement learning requires a large number of training samples generated by interacting with the environment; The learned command decision-making model has no initial experience, and first randomly explores in the huge policy space, which leads to low exploration efficiency, long training period and slow learning speed

[0004] Although the knowledge of prevention and control tasks is huge and complex, it is impossible to establish an intelligent expert system with a complete range of rules

However, the traditional command and decision-making method based on expert rules can effectively organize a large amount of empirical knowledge for the analysis and solution of practical problems.

Images