인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록·키워드
Objective: The aim of this study is to investigate the effects of Takeover Request Lead Time (TORlt) to Driver Workload in conditionally autonomous driving (CAD).
Background: Takeover request (TOR) is important issue in conditionally autonomous driving. A human driver must be ready to take control of the vehicle when TOR is given. However, driver could be underload when autonomous driving lasts for a long time or be overload if NDRT (Non-driving related task) is highly demanding or TOR appears suddenly. Therefore, investigating driver workload in takeover situation is essential. This paper focuses on effects of TORlt to driver workload.
Method: To investigate effects of TORlt to driver workload in CAD, experiment were conducted on the takeover situation through a driving simulator. Experiment were conducted on 7 levels of TORlt (3, 7, 10, 15, 30, 45, 60s) and ghost session. Also, the participants performed NDRT to assume CAD. During the experiments, subjective and physiological workload was measured by DALI (Driving Activity Load Index) and respiration rate respectively.
Results: TORlt has a large effect on driver workload. When TORlt was 3 seconds, the subjective and objective workload was the highest. As TORlt increases, both of workload decreases. For subjective workload, there was a slight increase in workload when TORlt was long, but it was not statistically significant. For physiological workload, the workload continued to decline, but there was no statistically significant difference for longer TORlt In addition, there was a significant positive correlation between subjective workload and physiological workload. Therefore, subjective workload can be replaced by physiological workload in takeover situation.
Conclusion: As TORlt increases, the driver workload decreases, but the difference is not significant if TORlt was long. Also, subjective workload measurement could be replaced by measuring physiological signals.
Application: Through this paper, it has been found that physiological measure could be an alternative for measuring workload in autonomous vehicle. Therefore, in autonomous vehicles, sensors that measure physiological signals will be installed to determine the driver`s workload.
Background: Takeover request (TOR) is important issue in conditionally autonomous driving. A human driver must be ready to take control of the vehicle when TOR is given. However, driver could be underload when autonomous driving lasts for a long time or be overload if NDRT (Non-driving related task) is highly demanding or TOR appears suddenly. Therefore, investigating driver workload in takeover situation is essential. This paper focuses on effects of TORlt to driver workload.
Method: To investigate effects of TORlt to driver workload in CAD, experiment were conducted on the takeover situation through a driving simulator. Experiment were conducted on 7 levels of TORlt (3, 7, 10, 15, 30, 45, 60s) and ghost session. Also, the participants performed NDRT to assume CAD. During the experiments, subjective and physiological workload was measured by DALI (Driving Activity Load Index) and respiration rate respectively.
Results: TORlt has a large effect on driver workload. When TORlt was 3 seconds, the subjective and objective workload was the highest. As TORlt increases, both of workload decreases. For subjective workload, there was a slight increase in workload when TORlt was long, but it was not statistically significant. For physiological workload, the workload continued to decline, but there was no statistically significant difference for longer TORlt In addition, there was a significant positive correlation between subjective workload and physiological workload. Therefore, subjective workload can be replaced by physiological workload in takeover situation.
Conclusion: As TORlt increases, the driver workload decreases, but the difference is not significant if TORlt was long. Also, subjective workload measurement could be replaced by measuring physiological signals.
Application: Through this paper, it has been found that physiological measure could be an alternative for measuring workload in autonomous vehicle. Therefore, in autonomous vehicles, sensors that measure physiological signals will be installed to determine the driver`s workload.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-ECN-0101-2019-530-000667038
