Search

Your search keyword '"Heo, Jaeseok"' showing total 140 results
Start Over Author "Heo, Jaeseok"
140 results on '"Heo, Jaeseok"'

3. Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

Author

Oh, Jeongwoo, Lee, Gunmin, Park, Jeongeun, Oh, Wooseok, Heo, Jaeseok, Chung, Hojun, Kim, Do Hyung, Park, Byungkyu, Lee, Chang-Gun, Choi, Sungjoon, and Oh, Songhwai

Subjects
Computer Science - Robotics
Abstract

Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in autonomous driving, the ability to detect hazardous situations, which can be seen as an out-of-distribution (OOD) detection problem, becomes crucial. However, most conventional datasets only provide expert driving demonstrations, although some non-expert or uncommon driving behavior data are needed to implement a safety guaranteed autonomous driving platform. To this end, we present a novel dataset called the R3 Driving Dataset, composed of driving data with different qualities. The dataset categorizes abnormal driving behaviors into eight categories and 369 different detailed situations. The situations include dangerous lane changes and near-collision situations. To further enlighten how these abnormal driving behaviors can be detected, we utilize different uncertainty estimation and anomaly detection methods to the proposed dataset. From the results of the proposed experiment, it can be inferred that by using both uncertainty estimation and anomaly detection, most of the abnormal cases in the proposed dataset can be discriminated. The dataset of this paper can be downloaded from https://rllab-snu.github.io/projects/R3-Driving-Dataset/doc.html., Comment: 6 pages, 6 figures, 3 tables

Published
2021

13. In patients with late-life depression and cognitive decline, adding tDCS to cognitive training does not significantly affect depressive symptoms but shows potential benefits on cognition as measured by fMRI

Author

Ha, Junghee, primary, Fang, Yu, additional, Cron, Greg O., additional, Heo, Jaeseok, additional, Jung, Eunjin, additional, Lee, Deokjong, additional, Kim, Hyunjeong, additional, Kim, Eosu, additional, Park, Jin Young, additional, and Lee, Jin Hyung, additional

Published
2024
Full Text
View/download PDF

25. EEG Studies on Physical Discomforts Induced by Virtual Reality Gaming

Author

Heo, Jaeseok and Yoon, Gilwon

Abstract

Physical discomforts, such as sickness, experienced during virtual reality (VR) gaming were analyzed using electroencephalography (EEG). Correlations between the results of a survey on the physical discomforts felt during a head mounted 360° VR gaming and EEGs were analyzed. EEGs were measured using 19 electrodes before, during, and after VR gaming. The brain was categorized into eight regions and EEGs were analyzed for each region. After gaming, a questionnaire was completed, and correlations between the scores of nausea, ocular discomfort, and disorientation and EEGs were examined. Before and during VR, there were substantial changes in the absolute power and relative power bands depending on the region of interest. The analysis of correlations with the physical discomforts classified based on the questionnaire showed that the theta and beta waves from the occipital and temporal lobes exhibited significant correlations. The EEGs before and after VR gaming did not exhibit significant changes. In this study, a qualitative analysis on the physical discomforts occurring during VR was conducted based on EEG. We expect that EEG can be utilized in providing customized VR capable of minimizing physical discomforts by analyzing the EEG measured in real time and providing feedback to VR gaming.

Published
2024
Full Text
View/download PDF

29. Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities

Author

Oh, Jeongwoo, Lee, Gunmin, Park, Jeongeun, Oh, Wooseok, Heo, Jaeseok, Chung, Hojun, Kim, Do Hyung, Park, Byungkyu, Lee, Chang-Gun, Choi, Sungjoon, and Oh, Songhwai

Subjects
FOS: Computer and information sciences, Computer Science - Robotics, ComputerApplications_COMPUTERSINOTHERSYSTEMS, Robotics (cs.RO)
Abstract

Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in autonomous driving, the ability to detect hazardous situations, which can be seen as an out-of-distribution (OOD) detection problem, becomes crucial. However, most conventional datasets only provide expert driving demonstrations, although some non-expert or uncommon driving behavior data are needed to implement a safety guaranteed autonomous driving platform. To this end, we present a novel dataset called the R3 Driving Dataset, composed of driving data with different qualities. The dataset categorizes abnormal driving behaviors into eight categories and 369 different detailed situations. The situations include dangerous lane changes and near-collision situations. To further enlighten how these abnormal driving behaviors can be detected, we utilize different uncertainty estimation and anomaly detection methods to the proposed dataset. From the results of the proposed experiment, it can be inferred that by using both uncertainty estimation and anomaly detection, most of the abnormal cases in the proposed dataset can be discriminated. The dataset of this paper can be downloaded from https://rllab-snu.github.io/projects/R3-Driving-Dataset/doc.html., 6 pages, 6 figures, 3 tables

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results