Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning

Xinyue Hu; Huaizhi Jia; Jiangtao Huang; Ban Wang; Zhenghong Gao

doi:10.1007/978-981-99-0479-2_181

Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning

Xinyue Hu
, Huaizhi Jia
, Jiangtao Huang
, Ban Wang
, Zhenghong Gao

School of Aeronautics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Deep reinforcement learning is a popular topic in research right now. Because the agent is a black box with unexpected consequences, it is frequently utilized for simple activities, while complex and high-risk tasks are difficult to reassure. The canard rotor/wing (CRW) compound aircraft’s helicopter configuration now necessitates a faster control system than regular helicopters. The feasibility of using deep deterministic policy gradient algorithm (DDPG) instead of CRW lateral control law to tackle the problem of standard PID control’s reaction time not being quick enough to meet fast control was investigated. At the same time, a stable and effective reward function is designed by sensing the agent’s external situation. The experimental results show that after training, an agent with more advantages than PID control is obtained.

Original language	English
Title of host publication	Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022
Editors	Wenxing Fu, Mancang Gu, Yifeng Niu
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	1954-1962
Number of pages	9
ISBN (Print)	9789819904785
DOIs	https://doi.org/10.1007/978-981-99-0479-2_181
State	Published - 2023
Event	International Conference on Autonomous Unmanned Systems, ICAUS 2022 - Xi'an, China Duration: 23 Sep 2022 → 25 Sep 2022

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	1010 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	International Conference on Autonomous Unmanned Systems, ICAUS 2022
Country/Territory	China
City	Xi'an
Period	23/09/22 → 25/09/22

Keywords

CRW
DDPG
Deep reinforcement learning
Neural network

Access to Document

10.1007/978-981-99-0479-2_181

Cite this

Hu, X., Jia, H., Huang, J., Wang, B., & Gao, Z. (2023). Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning. In W. Fu, M. Gu, & Y. Niu (Eds.), Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022 (pp. 1954-1962). (Lecture Notes in Electrical Engineering; Vol. 1010 LNEE). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-99-0479-2_181

Hu, Xinyue ; Jia, Huaizhi ; Huang, Jiangtao et al. / Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning. Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022. editor / Wenxing Fu ; Mancang Gu ; Yifeng Niu. Springer Science and Business Media Deutschland GmbH, 2023. pp. 1954-1962 (Lecture Notes in Electrical Engineering).

@inproceedings{2dd38a52b1a047abae993852566cc556,

title = "Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning",

abstract = "Deep reinforcement learning is a popular topic in research right now. Because the agent is a black box with unexpected consequences, it is frequently utilized for simple activities, while complex and high-risk tasks are difficult to reassure. The canard rotor/wing (CRW) compound aircraft{\textquoteright}s helicopter configuration now necessitates a faster control system than regular helicopters. The feasibility of using deep deterministic policy gradient algorithm (DDPG) instead of CRW lateral control law to tackle the problem of standard PID control{\textquoteright}s reaction time not being quick enough to meet fast control was investigated. At the same time, a stable and effective reward function is designed by sensing the agent{\textquoteright}s external situation. The experimental results show that after training, an agent with more advantages than PID control is obtained.",

keywords = "CRW, DDPG, Deep reinforcement learning, Neural network",

author = "Xinyue Hu and Huaizhi Jia and Jiangtao Huang and Ban Wang and Zhenghong Gao",

note = "Publisher Copyright: {\textcopyright} 2023, Beijing HIWING Sci. and Tech. Info Inst.; International Conference on Autonomous Unmanned Systems, ICAUS 2022 ; Conference date: 23-09-2022 Through 25-09-2022",

year = "2023",

doi = "10.1007/978-981-99-0479-2\_181",

language = "英语",

isbn = "9789819904785",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "1954--1962",

editor = "Wenxing Fu and Mancang Gu and Yifeng Niu",

booktitle = "Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022",

}

Hu, X, Jia, H, Huang, J, Wang, B & Gao, Z 2023, Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning. in W Fu, M Gu & Y Niu (eds), Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022. Lecture Notes in Electrical Engineering, vol. 1010 LNEE, Springer Science and Business Media Deutschland GmbH, pp. 1954-1962, International Conference on Autonomous Unmanned Systems, ICAUS 2022, Xi'an, China, 23/09/22. https://doi.org/10.1007/978-981-99-0479-2_181

Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning. / Hu, Xinyue; Jia, Huaizhi; Huang, Jiangtao et al.
Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022. ed. / Wenxing Fu; Mancang Gu; Yifeng Niu. Springer Science and Business Media Deutschland GmbH, 2023. p. 1954-1962 (Lecture Notes in Electrical Engineering; Vol. 1010 LNEE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning

AU - Hu, Xinyue

AU - Jia, Huaizhi

AU - Huang, Jiangtao

AU - Wang, Ban

AU - Gao, Zhenghong

PY - 2023

Y1 - 2023

N2 - Deep reinforcement learning is a popular topic in research right now. Because the agent is a black box with unexpected consequences, it is frequently utilized for simple activities, while complex and high-risk tasks are difficult to reassure. The canard rotor/wing (CRW) compound aircraft’s helicopter configuration now necessitates a faster control system than regular helicopters. The feasibility of using deep deterministic policy gradient algorithm (DDPG) instead of CRW lateral control law to tackle the problem of standard PID control’s reaction time not being quick enough to meet fast control was investigated. At the same time, a stable and effective reward function is designed by sensing the agent’s external situation. The experimental results show that after training, an agent with more advantages than PID control is obtained.

AB - Deep reinforcement learning is a popular topic in research right now. Because the agent is a black box with unexpected consequences, it is frequently utilized for simple activities, while complex and high-risk tasks are difficult to reassure. The canard rotor/wing (CRW) compound aircraft’s helicopter configuration now necessitates a faster control system than regular helicopters. The feasibility of using deep deterministic policy gradient algorithm (DDPG) instead of CRW lateral control law to tackle the problem of standard PID control’s reaction time not being quick enough to meet fast control was investigated. At the same time, a stable and effective reward function is designed by sensing the agent’s external situation. The experimental results show that after training, an agent with more advantages than PID control is obtained.

KW - CRW

KW - DDPG

KW - Deep reinforcement learning

KW - Neural network

UR - https://www.scopus.com/pages/publications/85151052102

U2 - 10.1007/978-981-99-0479-2_181

DO - 10.1007/978-981-99-0479-2_181

M3 - 会议稿件

AN - SCOPUS:85151052102

SN - 9789819904785

T3 - Lecture Notes in Electrical Engineering

SP - 1954

EP - 1962

BT - Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022

A2 - Fu, Wenxing

A2 - Gu, Mancang

A2 - Niu, Yifeng

PB - Springer Science and Business Media Deutschland GmbH

T2 - International Conference on Autonomous Unmanned Systems, ICAUS 2022

Y2 - 23 September 2022 through 25 September 2022

ER -

Hu X, Jia H, Huang J, Wang B, Gao Z. Intelligent Lateral Control of a Canard Rotor/Wing Aircraft Based on Reinforcement Learning. In Fu W, Gu M, Niu Y, editors, Proceedings of 2022 International Conference on Autonomous Unmanned Systems, ICAUS 2022. Springer Science and Business Media Deutschland GmbH. 2023. p. 1954-1962. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-99-0479-2_181