Reinforcement learning based attitude controller design

被引：0

作者：

Fu Y.-P. ^{[1
]}

Deng X.-Y. ^{[1
]}

He M. ^{[2
]}

Zhu Z.-Q. ^{[1
]}

Zhang L.-M. ^{[1
]}

机构：

[1] School of Aviation Support, Naval Aeronautical University, Yantai

[2] Command and Control Engineering Colledge, People’s Liberation Army Engineering University, Nanjing

来源：

Kongzhi yu Juece/Control and Decision | 2023年 / 38卷 / 09期

关键词：

attitude control; fixed-wing; !text type='JS']JS[!/text]BSim; PID; PPO; reinforcement learning;

D O I：

10.13195/j.kzyjc.2021.2230

中图分类号：

学科分类号：

摘要：

This article presents an attitude controller based on reinforcement learning (RL). The inputs of the actor network are states of attitude angle, angular rates etc, where the output is the angle control command of elevator and aileron, achieving the rapid response of the attitude angle with variable initial conditions, avoiding the application of the conventional PID controller and the parameter adjustment. According to the states transfer characteristics, by setting the splitting neural network model, the efficiency of algorithms is improved. In order to be close to the actual fixed-wing aircraft model, the simulation is based on the JSBSim F-16 aerodynamic model, using the OpenAI gym to build the simulation environment for reinforcement learning. With arbitrary angular speed, angle, and airspeed as initial conditions, the actor and critic networks are trained. The simulation results show that the RL based attitude controller has faster response and less dynamic error compared with the conventional PID controller. © 2023 Northeast University. All rights reserved.

引用

页码：2505 / 2510

页数：5

共 21 条

[1] Wang C, Yan C, Xiang X J, Et al., A continuous actor-critic reinforcement learning approach to flocking with fixed-wing UAVs, The 11th Asian Conference on Machine Learning, pp. 1-8, (2019)
[2] Huang X, Luo W Y, Liu J R., Attitude control of fixed-wing UAV based on DDQN, Chinese Automation Congress, pp. 4722-4726, (2019)
[3] Visioli A., Practical PID control, pp. 209-250, (2006)
[4] Wang J, Gao Z H., The automatic flight simulation of waypoint flight, Flight Dynamics, 26, 1, pp. 75-78, (2008)
[5] Shu H L., PID neural network for decoupling control of strong coupling multivariable time-delay systems, Control Theory and Applications, 15, 6, pp. 920-924, (1998)
[6] Yu D J, Long W Z, He J B., PID neural network decoupling control of multi-variable system and its application, Proceedings of the 6th International Conference on Information Engineering for Mechanics and Materials, pp. 277-282, (2016)
[7] Xu H, Lai J G, Yu Z H, Et al., Based on neural network PID controller design and simulation, Proceedings of the 2012 2nd International Conference on Computer and Information Applications, pp. 508-511, (2012)
[8] Peng Z H, Wang D, Zhang H W, Et al., Distributed neural network control for adaptive synchronization of uncertain dynamical multiagent systems, IEEE Transactions on Neural Networks and Learning Systems, 25, 8, pp. 1508-1519, (2014)
[9] Chen M, Ge S S, How B V E., Robust adaptive neural network control for a class of uncertain MIMO nonlinear systems with input nonlinearities, IEEE Transactions on Neural Networks, 21, 5, pp. 796-812, (2010)
[10] Sufiyan D, Win L T S, Win S K H, Et al., A reinforcement learning approach for control of a nature-inspired aerial vehicle, International Conference on Robotics and Automation, pp. 6030-6036, (2019)

← 1 2 3 →