DDPG-based unmanned aerial vehicle autonomous guidance control method

Abstract

The invention provides a DDPG (Deep Deterministic Policy Gradient)-based unmanned aerial vehicle autonomous guidance control method. The method comprises the steps of: establishing an unmanned aerialvehicle three-degree-of-freedom motion model, an unmanned aerial vehicle maneuvering control model, a reference terrain three-dimensional model and a peak three-dimensional model; calculating a terrain obstacle influence degree value of an unmanned aerial vehicle at the current position; constructing an evaluation network, a strategy network and a corresponding target network, and training the evaluation network and the strategy network; and using the training result as an unmanned aerial vehicle flight control outer loop controller to control the two-way overload and the unmanned aerial vehicle speed inclination angle of the unmanned aerial vehicle. According to the method, a deep reinforcement learning method is combined with unmanned aerial vehicle guidance control, learning training iscarried out in an offline simulation environment, practical application is carried out after requirements are met, the autonomy of the unmanned aerial vehicle in the task execution process is greatlyenhanced, and the task execution efficiency of the unmanned aerial vehicle is improved.

Description

technical field [0001] The invention relates to the fields of flight maneuver control and artificial intelligence, in particular to a method for autonomous guidance and control of an unmanned aerial vehicle. Background technique [0002] In recent years, with the development of drone technology, the performance of drones has improved rapidly. Whether it is military drones or civilian drones, various new technologies have emerged in an endless stream. Among them, improving the autonomous flight capability of UAVs, reducing human intervention, and avoiding human errors are the research priorities of UAV researchers in various countries. The traditional flight guidance control method of UAV usually realizes the flight guidance of UAV by designing a trajectory tracking controller after obtaining the flight path in the required task area. The controller mostly adopts PID control, linear binary Secondary regulators, synovial control, model predictive control, and adaptive control...

AI Technical Summary

Problems solved by technology

However, when the environment changes greatly, none of the above-mentioned trajectory tracking controllers has the ability to independently solve emergencies. Only after the UAV operator manually intervenes, the UAV can continue to complete the task. Improve the efficiency of UAV missions

Images