A5074776749- Autonomous Vehicle Technology and Safety
- Robotic Path Planning Algorithms
- Traffic control and management
- Vehicle Dynamics and Control Systems
- DNA Repair Mechanisms
- Smart Parking Systems Research
- Human-Automation Interaction and Safety
- Advanced Measurement and Metrology Techniques
- PARP inhibition in cancer therapy
- Advanced Neural Network Applications
- Viral Infections and Outbreaks Research
- Older Adults Driving Studies
- Genomics and Chromatin Dynamics
- CRISPR and Genetic Engineering
- Viral Infections and Vectors
- Advanced Numerical Analysis Techniques
- Soil Mechanics and Vehicle Dynamics
- Robotics and Sensor-Based Localization
- Automotive and Human Injury Biomechanics
- Neural Networks and Applications
- Scientific Measurement and Uncertainty Evaluation
- Fire effects on ecosystems
- Ubiquitin and proteasome pathways
- Advanced Statistical Methods and Models
- Machine Learning and Data Classification
Soonchunhyang University
2023-2025
Yonsei University
2013-2019
Ansan University
2018
Korea University
2018
Sejong University
2018
The convergence of mechanical, electrical, and advanced ICT technologies, driven by artificial intelligence 5G vehicle-to-everything (5G-V2X) connectivity, will help to develop high-performance autonomous driving vehicles services that are usable convenient for self-driving passengers. Despite widespread research on self-driving, user acceptance remains an essential part successful market penetration; this forms the motivation behind studies human factors associated with shuttle services. We...
This paper issues an integrated control system of self-driving autonomous vehicles based on the personal driving preference to provide personalized comfortable experience vehicle users. We propose Occupant's Preference Metric (OPM) which is defining a preferred lateral and longitudinal acceleration region with maximum allowable jerk for Moreover, we controller parameters enabling via preference-aware maneuvering vehicles. The proposed not only provides criteria occupant's preference, but...
Abstract We investigated potential nosocomial aerosol transmission of severe fever with thrombocytopenia syndrome virus (SFTSV) droplet precautions. During generating procedures, SFTSV was be transmitted from person to through aerosols. Thus, airborne precautions should added standard avoid direct contact and transmission.
The TopBP1-ATR axis is critical for maintaining genomic stability during DNA replication stress, yet the precise regulation of TopBP1 in stress responses remains poorly understood. In this study, we identified PHD and Ring Finger Domains 1 (PHRF1) as an important ATR activator through its interaction with TopBP1. Our analysis revealed a correlation between PHRF1 cancer patients. Mechanistically, recruited to lesions manner dependent on domain histone methylation. Subsequently,...
The present paper demonstrates a feasible real-time path planning algorithm and tracking method for autonomous driving vehicles based on 5 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> -order Bézier curve. It is demonstrated that -degree curve required to generate achieve lane change maneuvers in dynamic on-road environment. steering rate control input calculated the curvature extracted from generated trajectory. Matlab simulations...
Many significant research achievements in the past few decades have demonstrated that convolutional neural networks (CNNs) could be capable of steering wheel control which is basic and essential maneuver autonomous vehicles. We propose an end-to-end controller with CNN-based closed-loop feedback for vehicles improves driving performance compared to traditional approaches. This paper demonstrates proposed network, DAVE-2SKY, able learn inference angles lateral self-driving through initial...
We propose a real-time near-optimal motion and trajectory planner using an interior-point method (IPM) based simultaneous dynamic optimization approach applicable to automatic parallel parking. Partitioning parking zone into two areas with without inequality constraints drastically improves the convergence efficiency of IPM-based nonlinear programs while retaining accuracy stability simulation for optimization. An optimal ready-to-reverse point (RRP), from where backward moving maneuver...
Comfort driving has emerged as an important topic in the autonomous car research field. This study focuses on lane change maneuvering (LCM) of vehicles to provide a comfortable experience for passengers. For this purpose, we propose LCM algorithm determining desired trajectory by evaluating allowable lateral acceleration value obtained from Bezier curves at local path planning stage and smooth motion vehicle. The performance proposed was verified through computer simulations real tests.
This paper proposes a planning method based on forward path generation and backward tracking algorithm for Automatic Parking Systems, especially suitable parking situations. The is the steering property that moving trajectory coincides with identical angle. basic divided into two segments: collision-free locating segment an entering considers continuous angles connecting paths. MATLAB simulations were conducted, along experiments involving parallel perpendicular
We propose an artificial deep neural network- (ANN-) based automatic parking controller that overcomes a stubborn restriction prevalent in traditional approaches. The proposed ANN learns human-like control laws for through supervised learning from training database generated by computer-aided optimizations or real experiments. By the relationships between instantaneous vehicle states and corresponding maneuver parameters, twin yields lateral longitudinal maneuvering parameters executing...
We present an integrated lateral and longitudinal control system to ensure the dynamic stability tracking performance of autonomous vehicle. The velocity a vehicle is determined by considering road geometry information, including friction factor, bank angle, curvature road. proposed method makes strategy suitable for either low or high speed vehicles. controller was evaluated using Matlab simulations, experimental test autonomously steered underway.
One of crucial concern autonomous vehicles is that driver may experience discomfort, if the driving pattern vehicle quite different from her/his personal style.This study focuses on an control based user's preference adopted to provide a personalized and familiar users.For this purpose, we defined driver's metric (DPM) reflect their own style by specifying preferred lateral longitudinal acceleration region.Moreover, also proposed time optimal speed planning utilize DPM parameters extracted...
The majority of currently used automatic parking systems exploit the planning-and-tracking approach that involves planning reference trajectory first and then tracking desired trajectory. However, response delay longitudinal velocity prevents controller from tracing because vehicle’s other state parameters are not synchronized, while maneuvers vehicle according to planned steering profiles. We propose an inverse model provide a neural-network-based integrated lateral controller. approximated...
In fully autonomous vehicles, occupants do not need to keep their eyes forward during driving and they are able sit on any position, from a forward-facing position backward-facing. However, traditional passive safety systems such as seat belts, airbags, air curtains have been developed only for the driver or passengers sitting facing seats. this paper, we propose pre-crash system an occupant backward in front-end crashes. The proposed starts move horizontally tilt seatback prior collision...
Nowadays, most researchers in machine learning field will agree that the deep neural networks(DNNs) provide best performance pattern recognition, computer vision, natural language processing and so on. So many DNNs architectures are built relying on mathematical heuristics prior knowledge. We can make some new models by ourselves depending platforms, type of data applications. If we experiment all possible cases, then find approximate solution. Unfortunately, it is hard to do like because...
This paper discusses the advantages, disadvantages and methodology of maximum likelihood estimators (MLEs) applied to tracking problems. The goes on explain how a criterion derived by Akaike can, in conjunction with fit, be used help optimise size vector unknown parameters representing target kinematics. Some concepts discussed are illustrated numerical results relating simple bearings-only passive problem.
Theoretical limits to the accuracy with which target trajectory parameters can be estimated from stochastic data are derived via Cramer-Rao bound. As examples of their use, applied a simple one-dimensional tracking exercise and more complicated bearings-only problem.