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
(한양대학교) (한양대학교) (한양대학교)
저널정보
한국자동차공학회 한국자동차공학회 추계학술대회 및 전시회 2025년 한국자동차공학회 추계학술대회 및 전시회
오류 신고하기

피인용 0

검색

    초록·키워드

    In real-world autonomous driving scenarios, the accuracy of vehicle trajectory prediction is often constrained by limited observation ranges caused by sensor range limitations, occlusions, or environmental variability. Although many deep learning–based models have demonstrated promising results on public benchmarks with fixed and sufficiently wide observation ranges, their performance degrades significantly when the available observation length is reduced. This discrepancy highlights the importance of developing prediction models that are robust to variations in observation conditions. To address this problem, the present study investigates how observation range influences trajectory prediction performance and proposes a training strategy that enhances robustness against such variations. Specifically, we analyze state-of-the-art models under different observation settings and introduce a method that randomly varies the observation range during training to improve adaptability. The proposed approach enables the model to generalize across diverse observation scenarios and maintain stable performance even under restricted sensing conditions.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-151-26-02-095660758