Suhong Kim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Suhong Kim has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Chang-Joo Moon
Konkuk University
3 shared publications - Hyeongju Choi
Department of Smart Vehicle Engineering, Konkuk University, Seoul 05029, Republic of Korea
2 shared publications - Hyunseo Shin
Department of Smart Vehicle Engineering, Konkuk University, Seoul 05029, Republic of Korea
2 shared publications - Dongwon Hong
Department of Smart Vehicle Engineering, Konkuk University, Seoul 05029, Republic of Korea
1 shared publication - Jeongmin Moon
Department of Smart Vehicle Engineering, Konkuk University, Seoul 05029, Republic of Korea
1 shared publication - Juhum Kweon
Graduate School of Future Defense Technology Convergence, Konkuk University, Seoul 05029, Republic of Korea
1 shared publication
Latest Publications
- Open Access
- 14 September 2025
- Published by MDPI AG in Electronics
- Vol. 14 (18) , 3635
A Dynamic Bridge Architecture for Efficient Interoperability Between AUTOSAR Adaptive and ROS2
The automotive industry is undergoing a transition toward Software-Defined Vehicles (SDVs), necessitating the integration of AUTOSAR Adaptive, a standard for vehicle control, with ROS2, a platform for autonomous driving research. However, current static bridge approaches present notable limitations, chiefly regarding unnecessary resource consumption and compatibility issues with Quality of Service (QoS). To tackle these challenges, in this paper, we put forward a dynamic bridge architecture consisting of three components: a Discovery Manager, a Bridge Manager, and a Message Router. The proposed dynamic SOME/IP-DDS bridge dynamically detects service discovery events from the SOME/IP and DDS domains in real time, allowing for the creation and destruction of communication entities as needed. Additionally, it automatically manages QoS settings to ensure that they remain compatible. The experimental results indicate that this architecture maintains a stable latency even with a growing number of connections, demonstrating high scalability while also reducing memory usage during idle periods compared to static methods. Moreover, real-world assessments using an autonomous driving robot confirm its real-time applicability by reliably relaying sensor data to Autoware with minimal end-to-end latency. This research contributes to expediting the integration of autonomous driving exploration and production vehicle platforms by offering a more efficient and robust interoperability solution.
- 14 September 2025
- Published by MDPI AG in Electronics
- Vol. 14 (18) , 3635
Open AccessA Dynamic Bridge Architecture for Efficient Interoperability Between AUTOSAR Adaptive and ROS2
The automotive industry is undergoing a transition toward Software-Defined Vehicles (SDVs), necessitating the integration of AUTOSAR Adaptive, a standard for vehicle control, with ROS2, a platform for autonomous driving research. However, current static bridge approaches present notable limitations, chiefly regarding unnecessary resource consumption and compatibility issues with Quality of Service (QoS). To tackle these challenges, in this paper, we put forward a dynamic bridge architecture consisting of three components: a Discovery Manager, a Bridge Manager, and a Message Router. The proposed dynamic SOME/IP-DDS bridge dynamically detects service discovery events from the SOME/IP and DDS domains in real time, allowing for the creation and destruction of communication entities as needed. Additionally, it automatically manages QoS settings to ensure that they remain compatible. The experimental results indicate that this architecture maintains a stable latency even with a growing number of connections, demonstrating high scalability while also reducing memory usage during idle periods compared to static methods. Moreover, real-world assessments using an autonomous driving robot confirm its real-time applicability by reliably relaying sensor data to Autoware with minimal end-to-end latency. This research contributes to expediting the integration of autonomous driving exploration and production vehicle platforms by offering a more efficient and robust interoperability solution.
- Open Access
- 14 March 2025
- Published by MDPI AG in Electronics
- Vol. 14 (6) , 1138
Driver Identification System Based on a Machine Learning Operations Platform Using Controller Area Network Data
Ensuring vehicle security and preventing unauthorized driving are critical in modern transportation. Traditional driver identification methods, such as biometric authentication, require additional hardware and may not adapt well to changing driving behaviors. This study proposes a real-time driver identification system leveraging a Machine Learning Operations (MLOps)-based platform that continuously re-trains a deep learning model using vehicle Controller Area Network (CAN) data. The system collects CAN data, converts them into Markov Transition Field (MTF) images, and classifies drivers using a ResNet-18 model deployed on the Google Cloud Platform (GCP). An automated pipeline utilizing Pub/Sub, GCP Composer, and Vertex AI ensures continuous model updates based on newly uploaded driving data. Our experimental results demonstrate that models trained only on recent data significantly outperform those incorporating historical data, highlighting the necessity of frequent retraining. The intruder detection system effectively identifies unregistered drivers, further enhancing vehicle security. By automating model retraining and deployment, this system provides an adaptive solution that accommodates evolving driving behaviors, reducing reliance on static models. These findings emphasize the importance of real-time data adaptation in driver authentication systems, contributing to enhanced vehicle security and safety.
- 14 March 2025
- Published by MDPI AG in Electronics
- Vol. 14 (6) , 1138
Open AccessDriver Identification System Based on a Machine Learning Operations Platform Using Controller Area Network Data
Ensuring vehicle security and preventing unauthorized driving are critical in modern transportation. Traditional driver identification methods, such as biometric authentication, require additional hardware and may not adapt well to changing driving behaviors. This study proposes a real-time driver identification system leveraging a Machine Learning Operations (MLOps)-based platform that continuously re-trains a deep learning model using vehicle Controller Area Network (CAN) data. The system collects CAN data, converts them into Markov Transition Field (MTF) images, and classifies drivers using a ResNet-18 model deployed on the Google Cloud Platform (GCP). An automated pipeline utilizing Pub/Sub, GCP Composer, and Vertex AI ensures continuous model updates based on newly uploaded driving data. Our experimental results demonstrate that models trained only on recent data significantly outperform those incorporating historical data, highlighting the necessity of frequent retraining. The intruder detection system effectively identifies unregistered drivers, further enhancing vehicle security. By automating model retraining and deployment, this system provides an adaptive solution that accommodates evolving driving behaviors, reducing reliance on static models. These findings emphasize the importance of real-time data adaptation in driver authentication systems, contributing to enhanced vehicle security and safety.
- Open Access
- 12 July 2024
- Published by MDPI AG in Electronics
- Vol. 13 (14) , 2740
Enhancing Autonomous Driving Robot Systems with Edge Computing and LDM Platforms
The efficient operation and interaction of autonomous robots play crucial roles in various fields, e.g., security, environmental monitoring, and disaster response. For these purposes, processing large volumes of sensor data and sharing data between robots is essential; however, processing such large data in an on-device environment for robots results in substantial computational resource demands, causing high battery consumption and heat issues. Thus, this study addresses challenges related to processing large volumes of sensor data and the lack of dynamic object information sharing among autonomous robots and other mobility systems. To this end, we propose an Edge-Driving Robotics Platform (EDRP) and a Local Dynamic Map Platform (LDMP) based on 5G mobile edge computing and Kubernetes. The proposed EDRP implements the functions of autonomous robots based on a microservice architecture and offloads these functions to an edge cloud computing environment. The LDMP collects and shares information about dynamic objects based on the ETSI TR 103 324 standard, ensuring cooperation among robots in a cluster and compatibility with various Cooperative-Intelligent Transport System (C-ITS) components. The feasibility of operating a large-scale autonomous robot offloading system was verified in experimental scenarios involving robot autonomy, dynamic object collection, and distribution by integrating real-world robots with an edge computing–based offloading platform. Experimental results confirmed the potential of dynamic object collection and dynamic object information sharing with C-ITS environment components based on LDMP.
- 12 July 2024
- Published by MDPI AG in Electronics
- Vol. 13 (14) , 2740
Open AccessEnhancing Autonomous Driving Robot Systems with Edge Computing and LDM Platforms
The efficient operation and interaction of autonomous robots play crucial roles in various fields, e.g., security, environmental monitoring, and disaster response. For these purposes, processing large volumes of sensor data and sharing data between robots is essential; however, processing such large data in an on-device environment for robots results in substantial computational resource demands, causing high battery consumption and heat issues. Thus, this study addresses challenges related to processing large volumes of sensor data and the lack of dynamic object information sharing among autonomous robots and other mobility systems. To this end, we propose an Edge-Driving Robotics Platform (EDRP) and a Local Dynamic Map Platform (LDMP) based on 5G mobile edge computing and Kubernetes. The proposed EDRP implements the functions of autonomous robots based on a microservice architecture and offloads these functions to an edge cloud computing environment. The LDMP collects and shares information about dynamic objects based on the ETSI TR 103 324 standard, ensuring cooperation among robots in a cluster and compatibility with various Cooperative-Intelligent Transport System (C-ITS) components. The feasibility of operating a large-scale autonomous robot offloading system was verified in experimental scenarios involving robot autonomy, dynamic object collection, and distribution by integrating real-world robots with an edge computing–based offloading platform. Experimental results confirmed the potential of dynamic object collection and dynamic object information sharing with C-ITS environment components based on LDMP.