An autonomous generation method of UAV maneuvering strategy based on dqn

Abstract

The present invention provides a DQN-based method for autonomously generating a maneuvering strategy of an unmanned aerial vehicle, which respectively establishes a three-degree-of-freedom motion model of the unmanned aerial vehicle, a maneuvering control model of the unmanned aerial vehicle, a three-dimensional model of a reference terrain and a three-dimensional model of a mountain peak; The value of the influence degree of terrain obstacles in the position; build the evaluation network and the target network, and train the evaluation network; use the training result as the UAV flight control outer loop controller to control the two-way overload of the UAV and the speed of the UAV Tilt angle. The invention combines the deep reinforcement learning method with the guidance and control maneuvering strategy of the UAV, conducts learning and training in an offline simulation environment, and then implements practical application after meeting the requirements, which greatly enhances the UAV's ability to perform tasks. Autonomy, which improves the efficiency of UAVs in performing tasks.

Description

technical field [0001] The invention relates to the fields of flight maneuvering strategies and artificial intelligence, in particular to a method for autonomously generating maneuvering strategies of unmanned aerial vehicles. Background technique [0002] In recent years, with the development of unmanned aerial vehicle technology, the performance of unmanned aerial vehicle has been improved rapidly. Whether it is military unmanned aerial vehicle or civil unmanned aerial vehicle, various new technologies emerge one after another. 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 UAV flight guidance usually controls the maneuvering strategy of the UAV during the flight process to make it fly along the required flight path after obtaining the required flight path in the required mission area. The traditional maneuvering deci...

AI Technical Summary

Problems solved by technology

However, when the environment changes greatly, none of the above methods has the ability to solve emergencies autonomously. Only after the operator of the UAV manually intervenes, the UAV can continue to complete the task. This process greatly affects the ability of the UAV. Efficiency in performing tasks

Images