• Journal of Korean Society of Transportation
• /
• v.30 no.6
• /
• pp.27-36
• /
• 2012

In Korea, 28,641 cases of traffic accidents were caused by drunk driving in 2010. These statistics accounted for 12.62% of total number of traffic accidents. Moreover, the percentages of deaths and injuries from them were nearly 15% of those from whole traffic accidents. While police has emphasized enforcement efforts in order to reduce drunk driving, culture generous to drunk driving in addition to the absence of an appropriate intervention system for habitual drunk drivers have contributed to the increasing number of the drunk driving accidents in Korea. This study examined specific behavioral changes in drunk driving by comparing drivers' behavior pattern in non-alcoholic condition to those in alcoholic condition, using a psychomotor test and a driving simulator. In the psychomotor test measuring participants' reactions to the target stimulus, it was revealed that participants' correct responses were decreased, false responses were increased, and no responses also were increased after drinking. Furthermore, in the driving simulator performance after drinking, not only driving speed was faster but also the deviation of an accelerator pedal pressure and of the vehicle's lateral position were much increased. These results indicated that alcohol consumption would impair visio-cognitive ability and deteriorate driving safety. Finally, the implications and limitations of our findings and suggestions for the future research were discussed.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.297-305
• /
• 2017

As the development of autonomous vehicles becomes realistic, many automobile manufacturers and components producers aim to develop 'completely autonomous driving'. ADAS (Advanced Driver Assistance Systems) which has been applied in automobile recently, supports the driver in controlling lane maintenance, speed and direction in a single lane based on limited road environment. Although technologies of obstacles avoidance on the obstacle environment have been developed, they concentrates on simple obstacle avoidances, not considering the control of the actual vehicle in the real situation which makes drivers feel unsafe from the sudden change of the wheel and the speed of the vehicle. In order to develop the 'completely autonomous driving' automobile which perceives the surrounding environment by itself and operates, ability of the vehicle should be enhanced in a way human driver does. In this sense, this paper intends to establish a strategy with which autonomous vehicles behave human-friendly based on vehicle dynamics through the reinforcement learning that is based on Q-learning, a type of machine learning. The obstacle avoidance reinforcement learning proceeded in 5 simulations. The reward rule has been set in the experiment so that the car can learn by itself with recurring events, allowing the experiment to have the similar environment to the one when humans drive. Driving Simulator has been used to verify results of the reinforcement learning. The ultimate goal of this study is to enable autonomous vehicles avoid obstacles in a human-friendly way when obstacles appear in their sight, using controlling methods that have previously been learned in various conditions through the reinforcement learning.

• Journal of Drive and Control
• /
• v.18 no.4
• /
• pp.9-18
• /
• 2021

This study proposes a method for creating learning datasets to recognize obstacles using deep learning algorithms in automated construction machinery or an autonomous vehicle. Recently, many researchers and engineers have developed various recognition algorithms based on deep learning following an increase in computing power. In particular, the image classification technology and image segmentation technology represent deep learning recognition algorithms. They are used to identify obstacles that interfere with the driving situation of an autonomous vehicle. Therefore, various organizations and companies have started distributing open datasets, but there is a remote possibility that they will perfectly match the user's desired environment. In this study, we created an interface of the virtual simulator such that users can easily create their desired training dataset. In addition, the customized dataset was further advanced by using the RDBMS system, and the recognition rate was improved.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.196-196
• /
• 2000

This paper describes a lateral guidance system of an autonomous vehicle, using a neural network model of magneto-resistive sensor and magnetic fields. The model equation was compared with experimental sensing data. We found that the experimental result has a negligible difference from the modeling equation result. We verified that the modeling equation can be used in simulations. As the neural network controller acquires magnetic field values(B$\_$x/, B$\_$y/, B$\_$z/) from the three-axis, the controller outputs a steering angle. The controller uses the back-propagation algorithms of neural network. The learning pattern acquisition was obtained using computer simulation, which is more exact than human driving. The simulation program was developed in order to verify the acquisition of the teaming pattern, teaming itself, and the adequacy of the design controller. The performance of the controller can be verified through simulation. The real autonomous electric vehicle using neural network controller verified good results.

• Journal of Korean Society of Transportation
• /
• v.32 no.2
• /
• pp.106-118
• /
• 2014

The objective of this study is to develop a methodology for evaluating the effectiveness of in-vehicle pedestrian warning systems. Driving Simulator-based experiments were conducted to collect data to represent driver's responsive behavior. The braking frequency, lane change duration, and collision speed were used as measure of effectiveness (MOE) to evaluate the effectiveness. Collision speed data obtained from the simulation experiments were further used to predict pedestrian injury severity. Results demonstrated the effectiveness of warning information systems by reducing the pedestrian injury severity. It is expected that the proposed evaluation methodology and outcomes will be useful in developing various vehicular technologies and relevant policies to enhance pedestrian safety.

• Journal of Biomedical Engineering Research
• /
• v.38 no.2
• /
• pp.74-81
• /
• 2017

The purpose of this study was to investigate the EMG characteristics of driver's upper extremity and driving performance for manipulating brake and accelerator pedal by using left and right hand control devices during simulated driving. The people with disabilities in the lower limb have problems in operation of the motor vehicle because of functional loss for manipulating brake and accelerator pedal. Therefore, if hand control device is used for adaptive driving controls in people with lower limb impairments, the disabled people can improve their quality of life by driving a motor vehicle. Six subjects were participated in this study to evaluate driving performance and muscle activities for operating brake and accelerator pedal by using two different hand controls (steering column mounted hand control and floor mounted hand control) in driving simulator. We measured EMG activities of six muscles (posterior deltoid, middle deltoid, triceps, biceps, flexor carpi radialis, and extensor carpi radialis) during pushing and pulling movement with different hand controls for acceleration and braking. STISim Drive 3 software was used for the performance test of different hand control devices in straight lane course for time to reach target speed and brake reaction time. While pulling the hand control lever toward the driver, normalized EMG activities of middle deltoid, triceps and flexor carpi radialis in subjects with disabilities were significantly increased (p < 0.05) compared to the normal subjects. It was also found that muscle responses of posterior deltoid were significantly increased (p < 0.05) when using the right hand control than left hand control. While pushing the hand control lever forward away from the driver, normalized EMG activities of posterior deltoid, middle deltoid and extensor carpi radialis in subjects with disability were significantly increased (p < 0.05) compared to the normal subjects. It was shown that muscle responses of middle deltoid, biceps and extensor carpi radialis were significantly increased when using the right hand control than left hand control. Brake reaction time and time to reach target speed in subjects with disability was increased by 12% and 11.3% on average compared to normal subjects. The subjects with physical disabilities showed a tendency to relatively slow acceleration at the straight lane course.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.23-30
• /
• 2022

Recently, traffic congestion and environmental pollution have occurred due to population concentration and vehicle increase in large cities. Various studies are being conducted to solve these problems. Most of the traffic congestion in cities is caused by traffic signals at intersections. This paper proposes a dynamic traffic light control (DTLC) scheme to support safe vehicle operation and smooth traffic flow using real-time traffic information based on VANET. DTLC receives instantaneous speed and directional information of each vehicle through road side units (RSUs) to obtain the density and average speed of vehicles for each direction. RSUs deliver this information to traffic light controllers (TLCs), which utilize it to dynamically control traffic lights at intersections. To demonstrate the validity of DTLC, simulations were performed on average driving speed and average waiting time using the ns-2 simulator. Simulation results show that DTLC can provide smooth traffic flow by increasing average driving speed at dense intersections and reducing average waiting time.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.4
• /
• pp.31-43
• /
• 2019

Take-overs occur in autonomous vehicles at levels 3 and 4 based on SAE. For safe take-over, it is necessary to set the time required for diverse drivers to complete take-over in various road conditions. In this study, take-over time and stabilization characteristics were measured to secure safety of take-over in autonomous vehicle. To this end, a virtual driving simulator was used to set up situations similar to those on real expressways. Fifty drivers with various sexes and ages participated in the experiment where changes in traffic volume and geometry were applied to measure change in takeover time and stabilization characteristics according to various road conditions. Experimental results show that the average take-over time was 2.3 seconds and the standard deviation was 0.1 second. As a result of analysis of stabilization characteristics, there was no difference in take-over stabilization time due to the difference of traffic volume, and there was a significant difference by curvature changes.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.4
• /
• pp.55-62
• /
• 2012

In this study, it was observed through the ability of performing secondary tasks and baseline fetal heart rate how the supply of lavender, peppermint and highly concentrated oxygen (40%) affected distraction due to the performance of secondary tasks in the driving environment. Twelve male university students conducted secondary tasks while driving in the environments (6 in total) mixed and designed with oxygen concentration (21%, 40%) and the condition of odors (Normal, Lavender, Peppermint). The test was proceeded in order of stable state (5mins), driving (5mins), and secondary tasks (1min), and by extracting ECG data from every section by 30secs, the mean value of baseline fetal heart rate was calculated. As a result of analysis, in the ability of performing secondary tasks, a percentage of correct answers showed no difference in oxygen concentration and the condition of odors (p > 0.05). In performance completion time, a percentage of correct answers decreased showing a statistically significant difference in the condition of odors compared with the condition where odors were not provided (p < 0.05). As for baseline fetal heart rate, in the comparison between sections, while performing secondary tasks, it increased showing a significant difference compared with stable state and driving state (p < 0.05). The effect of interaction was observed in oxygen concentration and the condition of odors. When odors were not provided, baseline fetal heart rate decreased in 40% oxygen concentration compared with 21% oxygen concentration (p < 0.05), however, when peppermint was provided, it increased in 40% oxygen concentration compared with 21% oxygen concentration (p < 0.05). In conclusion, the fact that the condition of odors increased the ability of calculation, and when only the highly concentrated oxygen was provided, parasympathetic nerve system was activated, however, when highly concentrated oxygen was provided with peppermint at the same time, sympathetic nervous system (sns) was activated, which had a negative effect on the autonomic nervous system was drawn.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.235-249
• /
• 2020

The Ministry of Land, Infrastructure and Transport established safety standards for Level 3 autonomous vehicles for the first time in the world in December 2019, and specified the safety standards for conditional autonomous driving systems. Accordingly, it is necessary to analyze the influence of various driving environments on take-over. In this study, using a driving simulator, we investigated how traffic conditions and weather conditions affect take-over time and stabilization time. The experimental procedure was conducted in the order of preliminary training, practice driving, and test driving, and the test driving was conducted by dividing into a traffic density and geometry experiment and a weather environment experiment. As a result of the experiment, it was analyzed that the traffic volume and weather environment did not affect the take-over time and take-over stabilization time, and only the curve radius affects take-over stabilization time.