Jae-Kyung Cho

Jae-Kyung Cho

Auto-generated profile, based on publicly available information

Jae-Kyung Cho

SK Telecom, Seoul, Republic of Korea

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 December 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
MJMingu Jeon
Mingu Jeon
JCJae-Kyung Cho
Jae-Kyung Cho
HKHee-Yeun Kim
Hee-Yeun Kim
BPByeonggyu Park
Byeonggyu Park
SKSeong-Woo Kim
Seong-Woo Kim
SKSeong-Woo Kim
Seong-Woo Kim
Sound can be utilized to gather information about vehicles approaching a Non-Line-of-Sight (NLoS) region that remains hidden from Line-of-Sight (LoS) sensors due to its reflective and diffractive characteristics, like a radar. However, due to the inability to determine the location of NLoS vehicles in previous studies, it has not been possible to construct a sound-based active emergency braking system. This paper introduces a novel approach for localization of vehicles approaching in NLoS regions through sound. Specifically, a new particle filter method incorporating Acoustic-Spatial Pseudo-Likelihood (ASPLE) has been proposed to track objects using both acoustic and spatial information from the ego vehicle. Also, the Acoustic Recognition based Invisible-target Localization (ARIL) dataset, which is the firstly providing the location of the NLoS vehicle as ground truth using Bird’s Eye View camera, is proposed. The proposed method is validated using two datasets: the ARIL dataset and the Occluded Vehicle Acoustic Detection Dataset (OVAD) dataset. The proposed method exhibited remarkable performance in localizing NLoS targets in both datasets, predicting the location of the vehicle in the NLoS region. Lastly, the analysis of how the reflection of sound affects to the proposed method, highlighting variations based on the spatial situations, and demonstrate the empirical convergence of the method is described. Our code and dataset is available at https://github.com/mingujeon/NLoSVehicleLocalization.

8 July 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
CKChan Kim
Chan Kim
JCJae-Kyung Cho
Jae-Kyung Cho
HYHyung-Suk Yoon
Hyung-Suk Yoon
SKSeong-Woo Kim
Seong-Woo Kim
SKSeong-Woo Kim
Seong-Woo Kim
Deep reinforcement learning has been used to solve complex tasks in various fields, particularly in robotics control. However, agents trained using deep reinforcement learning have a problem of taking overconfident actions, even when the input state is far from the learned state distribution. This restricts deep reinforcement learning from being applied to real-world environments as overconfident actions in unlearned situations can result in catastrophic events; such as the collision of an autonomous vehicle. To address this, the agents should know “what they do not know” and choose an action by considering not only the state but also its uncertainty. In this study, we propose a novel uncertainty-conditioned policy (UNICON) inspired by the human behavior of changing policies according to uncertainty, e.g., slowing a car on a narrow road that has never been visited before. Our experimental results demonstrate that the proposed method is robust to unfamiliar scenarios that are not seen during training.

6 February 2022
Verified
Conference Paper
Closed access
JCJae-Kyung Cho
Jae-Kyung Cho
SJSihyeon Jo
Sihyeon Jo
SKSeong-Woo Kim
Seong-Woo Kim
SKSeong-Woo Kim
Seong-Woo Kim
Motion planning for autonomous driving in a dynamic environment is challenging in considering safety, efficiency, and passenger comfort. We clarify some scenarios in which previous multi-query motion planning methods demonstrate inefficient results, such as unnecessarily returning to the reference path and time delays due to myopic behavior. We propose a novel two-step method to address the problems. The myopic trajectory planning step uses an optimization method with the Frenet frame to generate exhaustive trajectory candidates on a very limited time horizon, which considers vehicle kinematics and dynamic safety. The non-myopic trajectory planning step uses variation in the rapidly exploring random tree to find the expected fastest trajectory to reach a local goal position among the results of the previous step. In 16.2% of entire random scenarios, our proposed method reduces the time to reach a destination by more than a 5% performance gap compared to other state-of-the-art motion planning methods.