Aircraft route tracking method based on deep reinforcement learning

Abstract

The invention relates to an aircraft route tracking method based on deep reinforcement learning, and belongs to the field of robot intelligent control. The aircraft route tracking method comprises thesteps of: constructing a Markov decision process model for aircraft trajectory tracking control, and respectively obtaining expressions of a state variable, a control variable, a transfer model and aone-step loss function for the aircraft route tracking control; respectively establishing a strategy network and an evaluation network; through reinforcement learning, enabling an aircraft to continuously update the strategy network and the evaluation network when making a step forward every time in route tracking control training until convergence; and obtaining a final strategy network for theroute tracking control. The aircraft route tracking method has strong expansibility, is not only suitable for the problem of route tracking control of the aircraft, but also can be expanded to other complicated problems of aircraft control by only resetting the state variable, a control input and a loss function and adjusting the structure and parameters of a neural network.

Description

technical field [0001] The invention relates to an aircraft route tracking method based on deep reinforcement learning, which belongs to the field of robot intelligent control. Background technique [0002] The autopilot system of an aircraft often includes two control loops: the outer loop generates the desired attitude according to the specified route; the inner loop controls the aircraft to track the instructions generated by the outer loop. Different from the outer loop controller, the inner loop controller is often only effective for specific aircraft and specific flight tasks. At present, most of the aircraft autopilot systems adopt the classic PID control. Although PID control is sufficient for most control tasks, its performance in dynamic environments such as wind disturbances, load changes, and voltage dips is not satisfactory. [0003] The flight path tracking control problem of aircraft is a very challenging research field, which has been developed for decades,...

AI Technical Summary

Problems solved by technology

Although PID control is sufficient for most control tasks, its performance is not satisfactory in dynamic environments, such as: wind disturbance, load changes, voltage dips, etc.

[0003] The flight path tracking control problem of aircraft is a very challenging research field, which has been developed for decades, but most of the research is still in the simulation stage, and there are very few control methods that can be put into practical application

However, it is difficult to obtain an accurate aircraft model in practical applications

Images