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
Seonghyeon Lim (Sogang University) Hyeonwoo Lee (Korea Advanced Institute of Science and Technology) Seunghyun Lee (Korea Advanced Institute of Science and Technology) Hyun Myung (Korea Advanced Institute of Science and Technology)
저널정보
제어로봇시스템학회 제어로봇시스템학회 국제학술대회 논문집 ICCAS 2024
발행연도
2024.10
수록면
1,510 - 1,515 (6page)

이용수

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

초록· 키워드

오류제보하기
Quadruped robots can perform various tasks across diverse terrains but face limitations due to the difficulty of interacting with environments. Adding manipulation capabilities allows these robots to handle more complex and varied tasks. However, designing a controller for legged manipulation is challenging due to the high degrees of freedom and model complexities, especially in challenging terrains. To address these issues, we present DreamTEAM, a novel framework for robust whole-body control in legged manipulation through learned terrain estimation. Utilizing deep reinforcement learning, DreamTEAM integrates an asymmetric actor-critic structure with a unified policy for both locomotion and manipulation, enabling quadruped robots to operate effectively using only proprioceptive sensors. Key features include a terrain estimator network that accurately estimates frontal terrain heights and an adaptive reward curriculum encouraging the robot to tackle more difficult manipulation tasks without compromising locomotion performance. The proposed method, DreamTEAM, validated its robustness and legged manipulation performance compared with other state-of-the-art methods through simulation experiments. Ablation studies highlight the importance of each module in the framework, showing how they contribute to overall stability and adaptability. This framework represents a substantial advancement in locomotion and manipulation, enhancing performance in challenging environments.

목차

Abstract
1. INTRODUCTION
2. DREAMTEAM
3. EXPERIMENTS
4. CONCLUSION
REFERENCES

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

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

최근 본 자료

전체보기

댓글(0)

0