Parameter design and optimization of a flight attitude simulator system based on PILCO framework

被引：0

作者：

Yang Y.-F. ^{[1
]}

Deng K. ^{[2
]}

Zuo Y.-Q. ^{[1
]}

Ban X.-J. ^{[1
]}

Huang X.-L. ^{[1
]}

机构：

[1] Center for Control Theory and Guidance Technology, Harbin Institute of Technology, Harbin

[2] Sichuan Academy of Aerospace Technology, Chengdu

来源：

Guangxue Jingmi Gongcheng/Optics and Precision Engineering | 2019年 / 27卷 / 11期

关键词：

Aircraft control; Parameter optimization; Probabilistic Inference for Learning Control(PILCO); Reinforcement learning;

D O I：

10.3788/OPE.20192711.2365

中图分类号：

学科分类号：

摘要：

Proportional-integral-derivative (PID) controllers are widely used in flight control systems. However, it is often very cumbersome to adjust the parameters of a PID controller. In this study, we use Probabilistic Inference for Learning Control (PILCO) to optimize the parameters of a PID controller. As the first step, we develop a probabilistic dynamics model of the flight control system using input and output data. Next, the existing PID controller is evaluated using the policy evaluation method. Finally, the evaluated PID controller is optimized by policy update. The sampling frequency of the system is 100 Hz and the data acquisition time per round is 8 s. The optimized PID controller can achieve stable control post 10 rounds of offline training. Through PILCO optimization, the flight attitude simulator performed robustly in a fixed-point experiment, indicating that PILCO has tremendous potential in solving nonlinear control and parameter optimization problems. © 2019, Science Press. All right reserved.

引用

页码：2365 / 2373

页数：8

共 14 条

[11]

Deisenroth M., Rasmussen C., PILCO: A model-based and data-efficient approach to policy search, International Conference on International Conference on Machine Learning, (2011)

[12]

Richard S., Andrew G., Reinforcement Learning: An Introduction, pp. 78-88, (2016)

[13]

Durrant-Whyte H., Roy N., Abbeel P., Learning to control a low-cost manipulator using data-efficient reinforcement learning, Robotics: Science and Systems VII, (2011)

[14]

Deisenroth M.P., Efficient Reinforcement Learning using Gaussian Processes, (2015)

← 1 2 →