메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
Minseok Jang (Konkuk University) Jeongseok Hyun (Konkuk University) Taeho Kwag (Konkuk University) Chan Gwak (Konkuk University) Chanyoung Jeong (Konkuk University) Tuan Anh Nguyen (Konkuk University) Jae-Woo Lee (Konkuk University)
저널정보
제어로봇시스템학회 제어로봇시스템학회 국제학술대회 논문집 ICCAS 2022
발행연도
2022.11
수록면
81 - 86 (6page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
Attitude stabilization is of paramount importance in the flight control of personal aerial vehicle (PAV) in the future urban air mobility (UAM). This study proposes to adopt a deep neural network (DNN) with exponentially stabilizing control Lyapunov functions (es-CLF) as a control framework (called, es-DNLC) for the stabilization of a KP-1 eVTOL PAV in multi-copter mode. The es-DNLC uses exponentially stabilizing control Lyapunov Function(es-CLF) as a learning policy in the DNN training to guarantee the robustness against disturbances. The robustness is enhanced and verified by an area increase of region of attraction (ROA) after adopting the trained DNN into the KP-1 control system. We implemented the proposed control framework in an open source autopilot system (PX4) along with software in the loop (SITL) in Gazebo simulator in which a wind gust is injected as a sudden disturbance in the simulation. A wind tunnel test was performed to increase the accuracy of the Gazebo simulation by utilizing high-fidelity propulsion data of the KP-1’s motors. The effectiveness of the adopted control framework is compared with linear quadratic regulator (LQR) which is also the initial control of es-DNLC before training. The finding of this study shows that es-DNLC compared to LQR can guarantee a higher level of robustness of the system against disturbances and aerodynamic uncertainties.

목차

Abstract
1. INTRODUCTION
2. RELATED WORKS
3. ES-DNLC : EXPONENTIALLY STABILIZING DEEP NEURAL LYAPUNOV CONTROL FRAMEWORK
4. DYNAMICS OF KP-1
5. SIMULATION RESULT
6. CONCLUSION
REFERENCES

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0