This paper presents a motion planning algorithm of autonomous racing vehicles for mimicking the characteristics of a human driver. Time optimal maneuver of a race car has been actively studied as a major research area over the past decades. Although the time optimization problem yields a single time series solution of minimum time maneuver inputs for the vehicle, human drivers achieve similar lap times while taking various racing lines and velocity profiles. In order to model the characteristics of a specific driver and reproduce the motion, a stochastic motion planning framework based on kernelized motion primitive is introduced. The proposed framework imitates the behavior of the generated reference motion, which is based on a small number of human demonstration laps along the racetrack using Gaussian mixture model and Gaussian mixture regression. The mean and covariance of the racing line and velocity profile mimicking the driver are obtained by accumulating the outputs tested at equidistantly sampled input points. The results confirmed that the obtained lateral and longitudinal motion simulates the driver's driving characteristics, which are feasible for actual vehicle test environments.

Side impact with MDB (moving deformable barrier) is common in side crash test protocols around the globe, most of which are quite similar to that of US NCAP side impact protocol but IIHS side impact protocol is considered to be the most harsh one due to the MDB's weight and impact speed. In this study US NCAP side impact and IIHS side impact test conditions are compared with respect to delta-V (impulse of the test vehicle), roll speed, and yaw speed as well as survival space (the smallest distance between the front driver seat cushion center to B pillar after the test). Error factors (friction between tire and ground, tolerance of vertical and longitudinal position of the MDB with respect to the test vehicle), which are resident in the test protocol is studied with respect to the global vehicle behavior (delta-V, roll, yaw) as well as survival space.

Many global car manufacturers in the world are recently developing a variety of electric vehicles in response to demanding market needs. Also, they have adapted the architecture method in order to develop electric vehicles effectively. It is because architecture method can produce various electric vehicles with high profitability. However, when electric vehicles are being developed, brake system has a lot of demanding tasks in relation to deciding specification of brake system because of heavy vehicle weight, narrow power electric room space and large volume of electric hydraulic booster. In this paper, a new approach is proposed for deciding the front and rear brake systems in order to design the brake system of electric vehicles effectively. To do this, we study correlations among vehicle weight, layout of power electric room and volume of electric hydraulic booster. And then, we also study combination of hydraulic braking and regenerative braking which is widely applied to electric vehicles. Finally, we want to contribute to build up modular design of brake system for architecture of electric vehicles through these studies.

This paper presents a multi-label lane detection method for autonomous vehicles based on deep learning. The proposed algorithm can detect two types of lanes: center lane and normal lane. The algorithm uses a convolution neural network with an encoder-decoder architecture to extract features from input images and produce a multi-label heatmap for predicting lane's label. This architecture has the potential to detect more diverse types of lanes in that it can add the number of labels by extending the heatmap's dimension. The proposed algorithm was tested on an OpenLane dataset and achieved 85 Frames Per Second (FPS) in end to-end inference time. The results demonstrate the usability and computational efficiency of the proposed algorithm for the lane detection in autonomous vehicles.

In order to verify autonomous driving scenarios and safety, a lot of driving and accident data is needed, so various organizations are conducting classification and analysis of traffic accident types. In this study, it was determined that accident recording devices such as EDR (Event Data Recorder) and DSSAD (Data Storage System for Automated Driving) would become an objective standard for analyzing the causes of autonomous vehicle accidents, and traffic accidents that occurred from 2015 to 2020 were analyzed. Using the database system of IGLAD (Initiative for the Global Harmonization of Accident Data), approximately 360 accident data of EDR-equipped vehicles were classified and their characteristics were analyzed by comparing them with accident types of ADAS (Advanced Driver Assistance System)-equipped vehicles. It will be used to develop autonomous vehicle accident investigation guidelines in the future.

With a sustained increase in the number of reported registrations for two-wheeled vehicles and the simultaneous growth of the domestic two-wheeled vehicle market, fueled by the activation of contactless industries and a rising population engaging in recreational two-wheeled vehicles during the COVID-19 era, concerns regarding safety incidents and environmental issues have come to the forefront. While the regular inspection methods and environmental standards for four-wheeled vehicles are becoming more stringent for safety and environmental management, the same cannot be said for two-wheeled vehicles. As the market for two-wheeled vehicles continues to expand, there is a pressing need for improvements in the management and inspection of these vehicles. In this study, we analyze cases of non-compliance from the results of periodic inspections over the past five years, specifically focusing on illegal customizations, exhaust emissions testing, and exhaust noise results. Through this analysis, we elucidate the necessity for enhancing the inspection system for two-wheeled vehicles, drawing parallels with the inspection systems applied to conventional automobiles. The findings of this research contribute to advocating for improvements in the inspection regime for two-wheeled vehicles, addressing the growing concerns related to safety and environmental impact.

This paper provides an analysis of the experimental procedures and results to ensure the reliability of the system manufactured for testing the hydrogen permeability of a 175 L compressed hydrogen container for a hydrogen bus. Based on the hydrogen permeability standard of 6 cc/(h·L), it was injected into the permeability test chamber at 10% intervals, and the permeated hydrogen concentration according to the injected amount was measured and compared with the actual amount of hydrogen permeated. As a result of the experiment, the measured value represented 96.34% of the actual permeation amount, which can be used as basic data for the hydrogen bus vessel permeability test system being built in Korea.

The advancement of autonomous driving technology is expected to transform cars beyond mere transportation into multifunctional spaces for relaxation and entertainment. As autonomous driving technology becomes more sophisticated, with no need for direct driver control, the interior space of vehicles is anticipated to be utilized for various purposes. Consequently, the importance of car seats, the component most frequently interacted with by passengers during travel, is expected to significantly rise. However, existing car seats are designed according to a seated posture, necessitating verification for passenger safety and seat structure considerations in the context of autonomous driving, where comfortable postures may differ. For these reasons, it is anticipated that the seats of future autonomous vehicles will evolve with the incorporation of additional safety and convenience features. In this study, a three-axis car simulator was employed to investigate seat angles for comfortable postures of passengers in autonomous driving scenarios. Representative postures were identified to enhance passenger convenience. Furthermore, functional design factors contributing to passenger comfort were applied to conduct seat design, seat structure, and collision analysis, with an analysis of the interrelationships among design factors.