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

논문 기본 정보

자료유형
학위논문
저자정보

남하종 (가톨릭대학교, 가톨릭대학교 대학원)

지도교수
최명걸
발행연도
2018
저작권
가톨릭대학교 논문은 저작권에 의해 보호받습니다.

이용수1

표지
AI에게 요청하기
추천
검색

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
본 논문에서는 인체 모션 데이터를 공간적 제약이 많은 환경 속에 있는 휴머노이드의 몸체에 맞추어 리타겟팅하는 기술을 소개한다. 주어진 모션 데이터는 물체를 손으로 잡거나 장애물 사이를 피해 다니는 등의 세밀한 인터랙션을 포함하고 있다고 가정한다. 또한 휴머노이드의 관절 구조는 인체 관절 구조와 다르며 주변 환경의 모양도 원본 모션이 촬영 될 당시와 서로 다르다고 가정한다. 이러한 조건 하에서 단순히 몸체의 변화만 고려한 리타겟팅 기법을 적용한다면 원본 모션 데이터에서 나타난 인터랙션의 내용을 그대로 보존하기 어렵다. 본 논문에서는 모션 데이터를 휴머노이드 몸체에 맞게 리타겟팅하는 문제와 인터랙션의 내용을 보존하는 문제를 나누어서 독립적으로 해결하는 방법을 제안한다. 제안된 방법은 세 단계로 구성된다. 첫 째, 환경 모델과의 인터랙션은 무시하고 모션 데이터를 휴머노이드 몸체에 맞게 리타겟팅 한다. 둘 째, 환경 모델의 모양을 휴머노이드 모션에 부합하도록 변형하여 원본 데이터에서 나타난 인터랙션이 재현되도록 한다. 마지막으로 휴머노이드 몸체와 환경 모델 사이의 공간적 상관 관계에 대한 제약 조건을 설정하고 환경 모델은 다시 원래 모양으로 되돌린다. 제안된 방법은 보스턴 다이나믹 사의 아틀라스 로봇 모델을 이용하여 수행된 실험을 통해 유용성을 검증하였다. 향후, 제안된 방법은 모션 데이터 트레킹을 통한 휴머노이드 동작 제어 문제에 사용될 수 있을 것으로 기대된다.

목차

목 차
초록 ······························································································································8
Ⅰ. 서론 ·······················································································································10
Ⅱ. 이론적 배경 및 관련 연구·················································································14
2.1이론적 배경 ··························································································14
2.1.1모션 데이터 ········································································14
2.1.2 정기구학 (Forward Kinematics) ·······························14
2.1.3 역기구학 (Inverse Kinematics) ·································16
2.2관련 연구 ······························································································18
2.2.1 휴머노이드 동작 제어·······················································18
2.2.2 물리기반 캐릭터 시뮬레이션···········································19
2.2.3 캐릭터 리타겟팅·································································19
Ⅲ. 실험방법 ···············································································································21
3.1 모션 리타겟팅·······················································································21
3.2 환경 모델 변형을 통한 인터랙션 복원···········································24
3.3 공간적 상관관계 계산 및 환경 모델 복원·····································27
3.3.1 상관관계 디스크립터 계산···············································27
3.3.2 환경 모델 복원과 관절 위치 계산·································29
Ⅳ. 실험 결과···············································································································32
Ⅴ. 결론 ·····················································································································37
5.1 연구 한계 및 토의···············································································37
5.2 향후 연구 제안·····················································································39
참고 문헌 ··················································································································40
영문 논문제출서 ······································································································45
영문 인준서 ··············································································································46
영문 초록 ····················································································································47

최근 본 자료

전체보기

댓글(0)

0