• Journal of Platform Technology
• /
• v.11 no.3
• /
• pp.24-31
• /
• 2023

Recently, interest in UAM (Urban Air Mobility, UAM), which can take off and land vertically in the operation of urban air transportation systems, has been increasing. Therefore, various start-up companies are developing related technologies as eco-friendly future transportation with advanced technology. However, studies on ways to increase safety in the operation of UAM are still insignificant. In particular, efforts are more urgent to improve the safety of risks generated in the process of attempting to land in the city center by UAM equipped with autonomous driving. Accordingly, this study proposes a plan to safely land by avoiding dangerous region that interfere when autonomous UAM attempts to land in the city center. To this end, first, the latitude and longitude coordinate values of dangerous objects observed by the sense of the UAM are calculated. Based on this, we proposed to convert the coordinates of the distorted planar image from the 3D image to latitude and longitude and then use the calculated latitude and longitude to compare the pre-learned feature descriptor with the HOG (Histogram of Oriented Gradients, HOG) feature descriptor to extract the dangerous Region. Although the dangerous region could not be completely extracted, generally satisfactory results were obtained. Accordingly, the proposed research method reduces the enormous cost of selecting a take-off and landing site for UAM equipped with autonomous driving technology and contribute to basic measures to reduce risk increase safety when attempting to land in complex environments such as urban areas.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.65-70
• /
• 2022

Lane change in urban environments is a challenge for both human-driving and automated driving due to their complexity and non-linearity. With the recent development of deep-learning, the use of the RNN network, which uses time series data, has become the mainstream in this field. Many researches using RNN show high accuracy in highway environments, but still do not for urban environments where the surrounding situation is complex and rapidly changing. Therefore, this paper proposes a lane change possibility decision network by adopting Attention layer, which is an SOTA in the field of seq2seq. By weighting each time step within a given time horizon, the context of the road situation is more human-like. A total 7D vectors of x, y distances and longitudinal relative speed of side front and rear vehicles, and longitudinal speed of ego vehicle were used as input. A total 5,614 expert data of 4,098 yield cases and 1,516 non-yield cases were used for training, and the performance of this network was tested through 1,817 data. Our network achieves 99.641% of test accuracy, which is about 4% higher than a network using only LSTM in an urban environment. Furthermore, it shows robust behavior to false-positive or true-negative objects.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.3
• /
• pp.83-95
• /
• 2022

This paper proposes a system that performs object detection and distance estimation for application to autonomous vehicles. Object detection is performed by a network that adjusts the split grid to the input image ratio using the characteristics of the recently actively used deep learning model YOLOv4, and is trained to a custom dataset. The distance to the detected object is estimated using a bounding box and homography. As a result of the experiment, the proposed method improved in overall detection performance and processing speed close to real-time. Compared to the existing YOLOv4, the total mAP of the proposed method increased by 4.03%. The accuracy of object recognition such as pedestrians, vehicles, construction sites, and PE drums, which frequently occur when driving to the city center, has been improved. The processing speed is approximately 55 FPS. The average of the distance estimation error was 5.25m in the X coordinate and 0.97m in the Y coordinate.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.487-488
• /
• 2023

전 세계적으로 도시화가 가속화됨에 따라 도시 내 차량의 수가 지속해서 증가하고 있지만 주차 공간의 부족으로 인해 도심 내 불법주차 문제가 심각해지고 있다. 또한 주차된 차량의 운전자 정보가 노출된 환경으로 인해 개인 정보 유출이 중요한 사회적 문제가 되고 있다. 따라서 본 논문에서는 불법주차 해소와 운전자 개인정보 보호를 동시에 해결하기 위한 자율주행 로봇 시스템을 제안한다. 제안한 방법에서는 정상 주차를 식별하기 방안으로 마커 인식을 적용하였고 ROS 기반 Stella N1을 사용하여 자율주행할 수 있는 로봇을 제작하였다. 또한 전화번호 없이 운전자와 연락을 취할 수 있는 메시지전달 앱을 개발하였다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.5
• /
• pp.200-209
• /
• 2018

This study proposed a method to select existing facilities as a landmark in order to reset accumulated errors of dead reckoning in a tunnel difficult to receive GNSS signals in automated driving. First, related standards and regulations were reviewed in order to survey 'variety' on shapes and installation locations as a feature of facilities. Second, 'recognition' on facilities was examined using image and Lidar sensors. Last, 'regularity' in terms of installation locations and intervals was surveyed through related references. The results of this study selected a fire fighting box / lamp (50m), an evacuation corridor lamp (300m), a lane control system (500m), a maximum / minimum speed limit sign and a jet fan as a candidate landmark to reset positioning errors. Based on those facilities, it was determined that error correction was possible. The results of this study are expected to be used in repositioning of automated driving vehicles in a tunnel.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.27 no.1
• /
• pp.29-40
• /
• 2024

Recently, the technology of autonomous driving, one of the core of the fourth industrial revolution, is developing, but sensor-based autonomous driving is showing limitations, such as accidents in unexpected situations, To compensate for this, HD-map is being used as a core infrastructure for autonomous driving, and interest in the public and private sectors is increasing, and various studies and technology developments are being conducted to secure the latest and accuracy of HD-map. Currently, NGII will be newly built in urban areas and major roads across the country, including the metropolitan area, where self-driving cars are expected to run, and is working to minimize data error rates through quality verification. Therefore, this study analyzes the spatial relationship of reference objects in the attribute structuring process for rapid and accurate renewal and production of HD-map under construction by NGII, By applying the attribute input automation methodology of the reference object in which spatial relations are established using the library of open source-based PyQGIS, target sites were selected for each road type, such as high-speed national highways, general national highways, and C-ITS demonstration sections. Using the attribute automation tool developed in this study, it took about 2 to 5 minutes for each target location to automatically input the attributes of the spatial relationship reference object, As a result of automation of attribute input for reference objects, attribute input accuracy of 86.4% for high-speed national highways, 79.7% for general national highways, 82.4% for C-ITS, and 82.8% on average were secured.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.14-19
• /
• 2021

This paper presents LiDAR static obstacle map based vehicle dynamic state estimation algorithm for urban autonomous driving. In an autonomous driving, state estimation of host vehicle is important for accurate prediction of ego motion and perceived object. Therefore, in a situation in which noise exists in the control input of the vehicle, state estimation using sensor such as LiDAR and vision is required. However, it is difficult to obtain a measurement for the vehicle state because the recognition sensor of autonomous vehicle perceives including a dynamic object. The proposed algorithm consists of two parts. First, a Bayesian rule-based static obstacle map is constructed using continuous LiDAR point cloud input. Second, vehicle odometry during the time interval is calculated by matching the static obstacle map using Normal Distribution Transformation (NDT) method. And the velocity and yaw rate of vehicle are estimated based on the Extended Kalman Filter (EKF) using vehicle odometry as measurement. The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment, and is verified with data obtained from actual driving on urban roads. The test results show a more robust and accurate dynamic state estimation result when there is a bias in the chassis IMU sensor.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.2
• /
• pp.39-44
• /
• 2022

This paper presents LiDAR static obstacle map based vehicle position correction algorithm for urban autonomous driving. Real Time Kinematic (RTK) GPS is commonly used in highway automated vehicle systems. For urban automated vehicle systems, RTK GPS have some trouble in shaded area. Therefore, this paper represents a method to estimate the position of the host vehicle using AVM camera, front camera, LiDAR and low-cost GPS based on Extended Kalman Filter (EKF). Static obstacle map (STOM) is constructed only with static object based on Bayesian rule. To run the algorithm, HD map and Static obstacle reference map (STORM) must be prepared in advance. STORM is constructed by accumulating and voxelizing the static obstacle map (STOM). The algorithm consists of three main process. The first process is to acquire sensor data from low-cost GPS, AVM camera, front camera, and LiDAR. Second, low-cost GPS data is used to define initial point. Third, AVM camera, front camera, LiDAR point cloud matching to HD map and STORM is conducted using Normal Distribution Transformation (NDT) method. Third, position of the host vehicle position is corrected based on the Extended Kalman Filter (EKF).The proposed algorithm is implemented in the Linux Robot Operating System (ROS) environment and showed better performance than only lane-detection algorithm. It is expected to be more robust and accurate than raw lidar point cloud matching algorithm in autonomous driving.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2016.05a
• /
• pp.207-208
• /
• 2016

By according to increase the research for autonomous vehicle in automobile industries, the efficient of autonomous cargo truck instead of conventional driver cargo truck will be analyzed in logistics areas. The inland transportation has been serious problem such as traffic accident, traffic congestion in downtown, air pollution, noise and etc. even if it have a great effect to logistics industries. Especially there have to be improved its transportation schedule and sleepy driving in night which induced heavy accident in highway. In this study, the effectiveness of autonomous cargo truck will be analysed by considering the logistics cost including social effects.

• Journal of Auto-vehicle Safety Association
• /
• v.9 no.2
• /
• pp.6-12
• /
• 2017

An autonomous driving system based on a precise digital map is developed. The system is implemented to the Hyundai's Tucsan fuel cell car, which has a camera, smart cruise control (SCC) and Blind spot detection (BSD) radars, 4-Layer LiDARs, and a standard GPS module. The precise digital map has various information such as lanes, speed bumps, crosswalks and land marks, etc. They can be distinguished as lane-level. The system fuses sensed data around the vehicle for localization and estimates the vehicle's location in the precise map. Objects around the vehicle are detected by the sensor fusion system. Collision threat assessment is performed by detecting dangerous vehicles on the precise map. When an obstacle is on the driving path, the system estimates time to collision and slow down the speed. The vehicle has driven autonomously in the Hyundai-Kia Namyang Research Center.