• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.5
• /
• pp.115-121
• /
• 2001

A driving load estimation method for intelligent cruise control(ICC) vehicles has been proposed in this paper. Vehicle driving load is one of the most important factors of perturbations in vehicle control and can affect the control performance critically. The effect of the control with driving load estimation on vehicle-to-vehicle distance control has been presented and investigated via computer simulations and vehicle tests. The results show that vehicle-driving-load-adaptive control can provide an ICC system with a good acceleration tracking performance. In addition, the results show that driving load estimation can compensate not only the variation of driving load but also the modeling errors.

• Proceedings of the KSME Conference
• /
• 2000.11a
• /
• pp.653-658
• /
• 2000

A driving load estimation method for intelligent cruise control(ICC) vehicles has been proposed in this paper. The driving load is one of the most important factors of perturbations in vehicle control and can affect the control performance critically. The Effect of the control with driving load estimation on vehicle-to-vehicle distance control has been presented and investigated via computer simulations and vehicle tests. The results show that the control with driving load estimation can provide ICC system with a good acceleration tracking performance. In addition, the results show that driving load estimation can compensate not only variation of driving load but also the modeling errors.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.603-616
• /
• 2021

Over the last few years, autonomous vehicles have progressed very rapidly. The odometry technique that estimates displacement from consecutive sensor inputs is an essential technique for autonomous driving. In this article, we propose a fast, robust, and accurate odometry technique. The proposed technique is light detection and ranging (LiDAR)-based direct odometry, which uses a spherical range image (SRI) that projects a three-dimensional point cloud onto a two-dimensional spherical image plane. Direct odometry is developed in a vision-based method, and a fast execution speed can be expected. However, applying LiDAR data is difficult because of the sparsity. To solve this problem, we propose an SRI generation method and mathematical analysis, two key point sampling methods using SRI to increase precision and robustness, and a fast optimization method. The proposed technique was tested with the KITTI dataset and real environments. Evaluation results yielded a translation error of 0.69%, a rotation error of 0.0031°/m in the KITTI training dataset, and an execution time of 17 ms. The results demonstrated high precision comparable with state-of-the-art and remarkably higher speed than conventional techniques.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.479-479
• /
• 2000

Recently, IVS(Intelligent Vehicle Systems) or ITS(Intelligent Traffic Systems) are much concerned subjects of automotive industry. In this paper, we will introduce an Intelligent Online Driving System for a car. This system allows the driver to be able to drive the car just by operating an integrated joystick. The proposed driving system could be implemented into any car and the key point of the design is that the driver still can drive the car as normal without using the joystick. Our Intelligent Online Driving System includes the integrated joystick, steering wheel control system, brake and acceleration (B&A)pedals control system, and the central control computer system. Steering wheel and B&A pedals are controlled by AC servo-motors. The integrated joystick generates the desired positions and the embedded computer controls these two servomotors to track the commands given by joystick. The control method for two servo-motors is PID control.

• Journal of Mechanical Science and Technology
• /
• v.15 no.6
• /
• pp.720-726
• /
• 2001

This paper describes a vehicle driving-load estimation method for application to vehicle Intelligent Cruise Control (ICC). Vehicle driving-load consists of aerodynamic force, rolling resistance, and gravitational force due to road slope and is unknown disturbance in a vehicle dynamic model. The vehicle driving-load has been estimated from engine and wheel speed measurements using a vehicle dynamic model a least square method. The estimated driving-load has been used in the adaptation of throttle/brake control law. The performance of the control law has been investigated via both simulation and vehicle tests. The simulation and test results show that the proposed control law can provide satisfactory vehicle-to-vehicle distance control performance for various driving situations.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.80-91
• /
• 2023

The purpose of this study is to suggest the direction for the development of intelligent agricultural machinery technology in the Republic of Korea. For this purpose, intelligent technology of agricultural machinery was divided into autonomous agricultural machinery and tractor-implement intelligent communication technology. Then, a survey and analysis of a previous study of the Republic of Korea and foreign countries were conducted. GNSS-based autonomous driving technology is still widely used worldwide, and recently, as research on camera and LiDAR-based autonomous driving is actively progressing, autonomous driving technology is becoming more advanced. ISOBUS-based technology is being developed worldwide for intelligent control of tractor-attached implements, and major global agricultural machinery manufacturers are actively applying it to their products. However, although some ISOBUS technologies are being researched in the Republic of Korea, there are no cases of application on agricultural machinery yet. Therefore, to be globally competitive in the agricultural machinery manufacturing industry, there is an urgent need to advance autonomous driving technology and commercialize agricultural machinery using ISOBUS technology.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.27 no.7
• /
• pp.1146-1151
• /
• 2003

In this paper, results of an analysis of driving behavior characteristics and a driver-adaptive control algorithm for adaptive cruise control systems have been described. The analysis has been performed based on real-world driving data. The vehicle longitudinal control algorithm developed in our previous research has been extended based on the analysis to incorporate the driving characteristics of the human drivers into the control algorithm and to achieve natural vehicle behavior of the adaptive cruise controlled vehicle that would feel comfortable to the human driver. A driving characteristic parameters estimation algorithm has been developed. The driving characteristics parameters of a human driver have been estimated during manual driving using the recursive least-square algorithm and then the estimated ones have been used in the controller adaptation. The vehicle following characteristics of the adaptive cruise control vehicles with and without the driving behavior parameter estimation algorithm have been compared to those of the manual driving. It has been shown that the vehicle following behavior of the controlled vehicle with the adaptive control algorithm is quite close to that of the human controlled vehicles. Therefore, it can be expected that the more natural and more comfortable vehicle behavior would be achieved by the use of the driver adaptive cruise control algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5299-5320
• /
• 2019

Interest in self-driving vehicle research has been rapidly increasing, and related research has been continuously conducted. In such a fast-paced self-driving vehicle research area, the development of advanced technology for better convenience safety, and efficiency in road and transportation systems is expected. Here, we investigate research in self-driving vehicles and analyze the main technologies of driverless car software, including: technical aspects of autonomous vehicles, traffic infrastructure and its communications, research techniques with vision recognition, deep leaning algorithms, localization methods, existing problems, and future development directions. First, we introduce intelligent self-driving car and road infrastructure algorithms such as machine learning, image processing methods, and localizations. Second, we examine the intelligent technologies used in self-driving car projects, autonomous vehicles equipped with multiple sensors, and interactions with transport infrastructure. Finally, we highlight the future direction and challenges of self-driving vehicle transportation systems.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.119-128
• /
• 2022

Recently, due to the development of related technologies for autonomous vehicles, driving work is changing more safely. However, the development of support technologies for level 5 full autonomous driving is still insufficient. That is, even in the case of an autonomous vehicle, the driver needs to drive through forward attention while driving. In this paper, we propose a method to monitor driving tasks by recognizing driver behavior. The proposed method uses pre-trained deep convolutional neural network models to recognize whether the driver's face or body has unnecessary movement. The use of pre-trained Deep Convolitional Neural Network (DCNN) models enables high accuracy in relatively short time, and has the advantage of overcoming limitations in collecting a small number of driver behavior learning data. The proposed method can be applied to an intelligent vehicle safety driving support system, such as driver drowsy driving detection and abnormal driving detection.

• 한국ITS학회:학술대회논문집
• /
• v.2006 no.10
• /
• pp.242-248
• /
• 2006