https://scholar.dgist.ac.kr/handle/20.500.11750/9960 2026-04-06T14:56:24Z 2026-04-06T14:56:24Z Seo, Ji Hwan Kim, Kyoung-Dae https://scholar.dgist.ac.kr/handle/20.500.11750/58291 2025-12-18T02:42:10Z 2025-02-28T15:00:00Z

Title: An RNN based Adaptive Hybrid Time Series Forecasting Model for Driving Data Prediction Author(s): Seo, Ji Hwan; Kim, Kyoung-Dae Abstract: In this paper, we propose a hybrid time series forecasting model, named as the Adaptive Multivariate Exponential Smoothing - Recurrent Neural Networks (AMES-RNN), which enables accurate prediction for time series data with non-seasonal and additive trend characteristics. To enhance prediction performance, the optimal smoothing parameters of the Exponential Smoothing (ES) model are estimated and updated online. Here, the parameter estimation is performed through a deep learning-based regression model, and a method for training the regression model is presented. In addition, the prediction model utilizes future-implying information as additional input if available in order to improve prediction accuracy. The effectiveness of the proposed model was validated through multistep forecast tests using vehicle driving data that has non-seasonal and additive trend characteristics. The results show that the prediction accuracy of the proposed model was improved at least 23.0% compared to those of the existing prediction model. Additionally, we demonstrated that AMES-RNN requires low computational resources, making it feasible to perform online predictions. © IEEE.

2025-02-28T15:00:00Z Seo, Ji Hwan Kwon, Seong Kyung Kim, Kyoung-Dae https://scholar.dgist.ac.kr/handle/20.500.11750/17170 2025-07-25T03:25:50Z 2022-07-31T15:00:00Z

Title: A discrete-time linear model predictive control for motion planning of an autonomous vehicle with adaptive cruise control and obstacle overtaking Author(s): Seo, Ji Hwan; Kwon, Seong Kyung; Kim, Kyoung-Dae Abstract: Motion planners for autonomous driving improve traffic safety through collision-free motion generation along the path. However, conventional motion planners render passengers uncomfortable as a result of jerky motion. To overcome this, we propose a model predictive control (MPC) based motion planner that not only ensures safety but also improves driving comfort. The proposed planner generates path tracking and collision-free maneuvers to ensure safety, and improve driving comfort by minimizing acceleration and jerk. Collision-free maneuvers include vehicle following and overtaking. The target speed is determined by comprehensively considering path tracking performance improvement and whether overtaking is possible. The speed of the vehicle is controlled by considering longitudinal acceleration and jerk minimization. The steering command is determined by considering both path tracking error reduction, and lateral acceleration and jerk minimization. In cases where vehicle overtaking is required and during high-speed driving conditions, the consideration of lateral acceleration and jerk minimization increases to improve driving comfort. The proposed planner is formulated as a convex optimization problem. The effectiveness of the proposed planner was evaluated in path tracking and collision avoidance simulations. The simulation results confirm that the proposed planner ensures vehicle safety through lane keeping and collision avoidance, and improves driving comfort.

2022-07-31T15:00:00Z Cho, Byeong-Moon Kim, Sangjun Kim, Kyoung-Dae Park, Kyung-Joon https://scholar.dgist.ac.kr/handle/20.500.11750/16516 2025-07-25T02:38:32Z 2022-01-31T15:00:00Z

Title: A Controller Switching Mechanism for Resilient Wireless Sensor–Actuator Networks Author(s): Cho, Byeong-Moon; Kim, Sangjun; Kim, Kyoung-Dae; Park, Kyung-Joon Abstract: Controller failures can result in unsafe physical plant operations and deteriorated performance in industrial cyber–physical systems. In this paper, we present a controller switching mechanism over wireless sensor–actuator networks to enhance the resiliency of control systems against problems and potential physical failures. The proposed mechanism detects controller failures and quickly switches to the backup controller to ensure the stability of the control system in case the primary controller fails. To show the efficacy of our proposed method, we conduct a performance evaluation using a hardware-in-the-loop testbed that considers both the actual wireless network protocol and the simulated physical system. Results demonstrate that the proposed scheme recovers quickly by switching to a backup controller in the case of controller failure. © 2022 by the authors. Licensee MDPI, Basel, Switzerland.

2022-01-31T15:00:00Z Lu, Qiang Jung, Hojin Kim, Kyoung-Dae https://scholar.dgist.ac.kr/handle/20.500.11750/16043 2025-07-25T02:43:52Z 2022-05-31T15:00:00Z

Title: An Optimization-based Approach for Resilient Connected and Autonomous Intersection Crossing Traffic Control under V2X Communication Author(s): Lu, Qiang; Jung, Hojin; Kim, Kyoung-Dae Abstract: In this paper, we present an optimization-based approach for safe, efficient, and resilient autonomous intersection traffic control in realistic vehicle-to-everything (V2X) communication environment. The proposed framework produces the fastest discrete-time trajectory for vehicles who want to cross an intersection. Constraints for safety are designed carefully in the optimization problem formulation to prevent potential collisions during intersection crossings. A novel vehicle-to-intersection (V2I) interaction mechanism is designed to handle imperfect communication characteristics such as packet delivery delay and loss. The proposed intersection management framework is evaluated by running extensive simulations using an open source vehicular network and microscopic traffic simulation software, Veins. The results show that the overall traffic control performance of the proposed framework is substantially better than conventional traffic light control framework, in particular when traffic volume is light and medium, even in situations with a realistic wireless vehicular network setting where packet delivery delays and drops occasionally occur. IEEE

2022-05-31T15:00:00Z