• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.464-470
• /
• 2021

Automobiles have been used as simple means of transportation, but recently, as automobiles are rapidly becoming intelligent and smart, and automobile preferences are increasing, research on IT technology convergence is underway, requiring basic high-performance functions such as driver's convenience and safety. As a result, autonomous driving and semi-autonomous vehicles are developed, and these technologies sometimes deviate from lanes due to environmental problems, situations that cannot be judged by autonomous vehicles, and lane detectors may not recognize lanes. In order to improve the performance of lane departure from the lane detection system of autonomous vehicles, which is such a problem, this paper uses fast recognition, which is a characteristic of YOLO(You only look once), and is affected by the surrounding environment using CSI-Camera. We propose a lane detection system that recognizes the situation and collects driving data to extract the region of interest.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1117-1123
• /
• 2021

Object recognition is to identify the location and class of a specific object by analyzing the given image when a specific image is input. One of the fields in which object recognition technology is actively applied in recent years is autonomous vehicles, and this paper describes the trend of image-based object recognition artificial intelligence technology in autonomous vehicles. The image-based object detection algorithm has recently been narrowed down to two methods (a single-step detection method and a two-step detection method), and we will analyze and organize them around this. The advantages and disadvantages of the two detection methods are analyzed and presented, and the YOLO/SSD algorithm belonging to the single-step detection method and the R-CNN/Faster R-CNN algorithm belonging to the two-step detection method are analyzed and described. This will allow the algorithms suitable for each object recognition application required for autonomous driving to be selectively selected and R&D.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.4
• /
• pp.161-172
• /
• 2023

Autonomous driving vehicles recognize the surroundings through various sensors mounted on the vehicle and control the vehicle based on the collected information. The level of autonomous driving technology is improving due to the development of sensor technology and algorithms that process collected data, but the implementation of perfect autonomous driving technology has not been achieved. To overcome these limitations, through autonomous cooperative driving centered on infrastructure. In this study, developed a position correction sign that provides a reference for positioning of autonomous vehicles. First of all, an analysis was performed on the current status of positioning technology for autonomous driving. And measure the number of point clouds for the 1st sample consisting of two square reflective surfaces and 2nd sample that increased the vertical length of each reflective surface. Experimental results show that both primary and secondary products are installed at least 15 m apart It could be recognized as a sensor, and it was confirmed that the secondary production that increased the length of the top and bottom had a higher number of point clouds than the primary production and better expressed the shape of the facility.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.107-112
• /
• 2003

In general, the dynamics of autonomous underwater vehicles(AUVs) are highly nonlinear and time-varying, and the hydrodynamic coefficients of vehicles are hard to estimate accurately because of the variations of these coefficients with different navigation conditions. For this reason, in this paper, the control gain function is assumed to be unknown and the exogenous input term is assumed to be unbounded, although it still satisfies certain restrict condition. And these two kinds of wild assumptions have been seldom handled simultaneously in one system because of the difficulty of stability analysis. Under the above two relaxed assumptions, a robust neural network control scheme is presented for autonomous diving control of an AUV, and can guarantee that all the signals in the closed-loop system are UUB (uniformly ultimately bounded). Some practical features of the proposed control law are also discussed.

• Journal of Power System Engineering
• /
• v.20 no.1
• /
• pp.24-29
• /
• 2016

Remotely operated vehicles or autonomous underwater vehicles have been used for exploiting seabed natural resources. In this study, the autonomous underwater vehicle of hovering type(HAUV) is developed to observe underwater objects in close distance. A dynamic model with six degrees of freedom is established, capturing the motion characteristics of the HAUV. The equations of motion are generated for the dynamic control simulation of the HAUV. The added mass, drag and lift forces are included in the computer model. Computational fluid dynamics simulation is carried out using this computer model. The drag coefficients are produced from the CFD.

• Journal of Ocean Engineering and Technology
• /
• v.26 no.4
• /
• pp.1-7
• /
• 2012

This paper deals with the global path planning problem for AUVs (autonomous underwater vehicles) in a tidal current field. The previous researches in the field were unsuccessful at simultaneously addressing the two issues of obstacle avoidance and tidal current-based optimization. The use of a genetic algorithm is proposed in this paper to move past this limitation and solve both issues at once. Simulation results showed that the genetic algorithm could be applied to generate an optimal path in the field of a tidal current with multiple obstacles.

• International Journal of Ocean System Engineering
• /
• v.2 no.3
• /
• pp.139-150
• /
• 2012

This paper presents an improved guidance algorithm for autonomous underwater vehicles (AUV) in 3D space for generating smoother vehicle turn during the course change at the way-points. The way-point guidance by the line-of-sight (LOS) method has been modified for correcting the reference angles to achieve minimal calculation and smoother transition at the way-points. The algorithm has two phases in which the first phase brings the vehicle to converge to a distance threshold point on the line segment connecting the first two way-points and the next phase generates an angular path with smoother transition at the way-points. Then the desired angles are calculated from the reference and correction angles. The path points are regularly parameterized in the spherical coordinates and mapped to the Cartesian coordinates. The proposed algorithm is found to be simple and can be used for real time implementation. The details of the algorithm and simulation results are presented.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.6
• /
• pp.592-600
• /
• 2010

The problem of motion control for AUV (Autonomous Underwater Vehicles) is addressed. The utilization of such robotic vehicles has gained an increasing importance in many marine activities. In this paper the objective is to describe how to design and apply FGS (Fuzzy Gain Scheduling) PD (Proportional Derivative) controller for an AUV (Autonomous Underwater Vehicle) to control the yaw and depth of the vehicle by keeping the path of the navigation to a desired point, and/or changing the path according to a set point.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.3
• /
• pp.154-163
• /
• 2013

In this paper, we propose a formation control algorithm for underactuated autonomous underwater vehicles (AUVs) with parametric uncertainties using the approach angle. The approach angle is used to solve the underactuated problem for AUVs, and the leader-follower strategy is used for the formation control. The proposed controller considers the nonzero off-diagonal terms of the mass matrix of the AUV model and the associated parametric uncertainties. Using the state transformation, the mass matrix, which has nonzero off-diagonal terms, is transformed into a diagonal matrix to simplify designing the control. To deal with the parametric uncertainties of the AUV model, a self-recurrent wavelet neural network is used. The proposed formation controller is designed based on the dynamic surface control technique. Some simulation results are presented to demonstrate the performance of the proposed control method.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1505-1515
• /
• 2016

The age of autonomous vehicles has come according to development of high performance sensing and artificial intelligence technologies. And importance of the vehicle's surrounding environment sensing and observation is increasing accordingly because of its stability and control efficiency. In this paper we propose an integrated platform for efficient networking, analysis and monitoring of multiple sensing data on the vehicle that are equiped with various automotive sensors such as GPS, weather radar, automotive radar, temperature and humidity sensors. From simulation results, we could see that the proposed platform could perform realtime analysis and monitoring of various sensing data that were observed from the vehicle sensors. And we expect that our system can support drivers or autonomous vehicles to recognize optimally various sudden or danger driving environments on the road.