메뉴 건너뛰기
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)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Gyeongsang National University)
저널정보
대한전기학회 전기학회논문지 전기학회논문지 제75권 제11호
오류 신고하기

피인용 0

검색

    초록·키워드

    Driving VLMs use Chain-of-Causation (CoC) to link scenes to behavior, but CoC may omit when a trajectory is executable. We propose Safety-Constrained CoC, appending a natural-language guard with activation, invariant, bound, prohibition, release, fallback, and termination clauses. Given a scene, CoC, guard, and trajectory candidates, the model selects one candidate; an external deterministic verifier compares its measurements with the guard. Our paired-contract benchmark changes only the guard while fixing the scene, objective, and candidates. In three-seed temporal tests with LoRA-tuned Qwen3-VL-2B-Instruct, the violation rate decreased from 0.319 without a guard to 0.000, while compliant completion and paired accuracy reached 1.000. For unseen time values, candidate accuracy, violation rate, and paired accuracy were 0.635, 0.351, and 0.306. The results support guard-conditioned synthetic candidate selection, not continuous trajectory generation or vehicle-level safety.

    최근 본 자료 전체보기