Aircraft attitude control method, system and device based on reinforcement learning

Abstract

The invention belongs to the field of aircraft control, and in particular relates to an aircraft attitude control method, system, and device based on reinforcement learning, aiming at solving the problem of realizing no-overshoot control under a low-precision model. The aircraft attitude control method based on reinforcement learning of the present invention includes: obtaining the aircraft state data at the first moment; calculating the expected attitude angle and the attitude angle tracking error based on the expected flight trajectory of the aircraft, and constructing the network input state at the first moment; The network input state, the desired attitude angle, and the optimal control action are obtained through the DDPG deep reinforcement learning network; the attitude adjustment of the aircraft is performed based on the optimal control action. The invention can realize no overshoot control under the low-precision model, has short adjustment time and small steady-state error.

Description

technical field [0001] The invention belongs to the field of aircraft control, and in particular relates to an aircraft attitude control method, system and device based on reinforcement learning. Background technique [0002] In recent years, aircrafts have been widely promoted and used in civil fields such as agricultural plant protection, power inspection, urban security, forest fire prevention, environmental monitoring, low-altitude aerial photography, and aerial search and rescue, and in military fields such as battlefield environmental reconnaissance, transportation support, and patrol surveillance. The aircraft has the advantages of fast maneuvering speed, wide coverage, the ability to observe the ground situation from the "God's perspective", and quick response to commands. It will become more popular and have richer application scenarios in the future. [0003] Attitude control is the core of aircraft flight control, and its quality directly affects the effect of the...

AI Technical Summary

Problems solved by technology

However, there are disturbances caused by unmodeled dynamics and uncertain items during the flight, such as gusts, parameter perturbations, etc., and time-varying disturbances. The debugging of parameters is more complicated and requires constant trial and error, which leads to a decrease in the stability margin of the aircraft control, and even the risk of loss of control

Images