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
Mineui Hong (Seoul National University) Songhwai Oh (Seoul National University)
저널정보
제어로봇시스템학회 제어로봇시스템학회 국제학술대회 논문집 ICCAS 2021
발행연도
2021.10
수록면
699 - 702 (4page)

이용수

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

초록· 키워드

오류제보하기
In this paper, we tackle the problem of efficient data-driven control of a system, of which the observations are given by raw images. By learning latent representations of image observations and their dynamics model, the image-based control problems can be handled by planning a sequence of controls in the learned latent space. However, these methods have a disadvantage that large amounts of transition data should be collected individually whenever the details of the observation models change (e.g. view-point, color of robots or backgrounds), even if the intrinsic system dynamics is the same. To tackle this issue, we present a method to leverage the data collected from different observation models to enhance the sample efficiency for learning the latent representation of the target domain. To this end, our method utilizes individual encoders for each observation model, and the encoders are trained with a cyclic loss function we propose, to learn the shared latent representation of the observations. The proposed method is demonstrated in a table-top manipulation task using Robosuite simulator [1], and shown to be able to reduce the sample complexity for learning the dynamics model with the data collected from a new view-point.

목차

Abstract
1. INTRODUCTION
2. BACKGROUND
3. PROPOSED METHOD
4. EXPERIMENTS
5. 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