• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1271-1281
• /
• 2017

It is essential to collect and analyze target information around the vehicle for autonomous driving of the vehicle. Based on the analysis, environmental information such as location and direction should be analyzed in real time to control the vehicle. In particular, obstruction or cutting of objects in the image must be handled to provide accurate information about the vehicle environment and to facilitate safe operation. In this paper, we propose a method to simultaneously generate 2D and 3D bounding box proposals using LiDAR Edge generated by filtering LiDAR sensor information. We classify the classes of each proposal by connecting them with Region-based Fully-Covolutional Networks (R-FCN), which is an object classifier based on Deep Learning, which uses two-dimensional images as inputs. Each 3D box is rearranged by using the class label and the subcategory information of each class to finally complete the 3D bounding box corresponding to the object. Because 3D bounding boxes are created in 3D space, object information such as space coordinates and object size can be obtained at once, and 2D bounding boxes associated with 3D boxes do not have problems such as occlusion.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.4
• /
• pp.351-360
• /
• 2022

Autonomous vehicles require precise knowledge of their position, velocity and orientation in all weather and traffic conditions in any time. And, these information is effectively used for path planning, perception, and control that are key factors for safety of vehicle driving. For this purpose, a high precision GNSS technology is widely adopted in autonomous vehicles as a core localization and navigation method. However, due to the lack of infrastructure as well as cost issue regarding GNSS correction data communication, only a few high precision GNSS technology will be available for future commercial autonomous vehicles. Recently, a high precision GNSS sensor that is based on a Broadcast-RTK system to dramatically reduce network maintenance cost by utilizing the existing broadcasting network is released. In this paper, we present the performance test result of the broadcast-RTK-based commercial high precision GNSS receiver to test the feasibility of the system for autonomous driving in Korea. Massive measurement campaigns covering of Korea region were performed, and the obtained measurements were analyzed in terms of ambiguity fixing rate, integer ambiguity loss recovery, time to retry ambiguity fixing, average correction information update rate as well as accuracy in comparison to other high precision systems.

• Journal of Information Technology Applications and Management
• /
• v.31 no.3
• /
• pp.39-52
• /
• 2024

The development of autonomous driving technology is expected to bring about a major change in the mobility rights of the transportation vulnerable. It is very important to identify user requirements in developing autonomous vehicles and service technologies for the transportation vulnerable. User requirements were derived for the wheelchair disabled and the walking disabled. Through focus interviews, a total of 58 requirements were derived for wheelchair-using disabled people and 53 requirements for walking disabled people. A Kano survey was conducted on 33 wheelchair disabled and 34 walking disabled. After that, the quality types of functional requirements in terms of autonomous vehicles and service environment development were analyzed using the Kano model. Priority analysis was conducted on the functions required by the wheelchair disabled and the walking disabled. The results of this study can be used as basic data to determine the priorities of user function requirements in the early stages of autonomous vehicle and service technology development.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.72-81
• /
• 2023

We introduce tightly-coupled GNSS-LiDAR-Inertial state estimator, which is capable of SLAM (Simultaneously Localization and Mapping) and autonomous driving. Long term drift is one of the main sources of estimation error, and some LiDAR SLAM framework utilize loop closure to overcome this error. However, when loop closing event happens, one's current state could change abruptly and pose some safety issues on drivers. Directly utilizing GNSS (Global Navigation Satellite System) positioning information could help alleviating this problem, but accurate information is not always available and inaccurate vertical positioning issues still exist. We thus propose our method which tightly couples raw GNSS measurements into LiDAR-Inertial SLAM framework which can handle satellite positioning information regardless of its uncertainty. Also, with NLOS (Non-light-of-sight) satellite signal handling, we can estimate our states more smoothly and accurately. With several autonomous driving tests on AGV (Autonomous Ground Vehicle), we verified that our method can be applied to real-world problem.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.3
• /
• pp.80-96
• /
• 2024

This study conducted over two rounds Delphi survey targeting experts in the fields of roads, transportation, automobiles, intelligent transport systems(ITS), and communications to analyze the direction of change in road design, operation, and systems in the Lv.4/4+ autonomous driving era. To construct the Delphi survey items, a basic survey was conducted. The first and second Delphi surveys targeted experts in fields closely related to autonomous driving. The results of the survey revealed an expectation that in the future, transportation operations would change focus to shared autonomous vehicle(AV) and public transportation transfers, and there would be corresponding changes in the cross-sectional configuration. Exclusive lanes for AV are expected to be introduced commencing from highways and general national roads, and there was a consensus that they should be installed in the center of the road rather than on the sides and would use the same lane width as that of the existing road. In terms of facilities for AVs, it was found that it would be necessary to expand pedestrian-vehicle separation facilities, insert communication chips into facilities for location recognition, advance precision maps, and expand roadside communication facilities.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.6
• /
• pp.43-49
• /
• 2022

FMCW(Frequency Modulated Continuous Wave) Radar is very useful for vehicle collision warning system and autonomous driving sensor. In this paper, the design and implementation of FMCW radar based on two chip MMIC developed as an autonomous driving sensor was described. Especially, generation of frame-based and chirp-based waveform generation and signal processing are mixed to have the strength of maximum detection speed and compensation of speed. This implemented system was analyzed for performance and commercialization potential through lab. test and driving test in K-city.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.2
• /
• pp.115-120
• /
• 2015

Recently, in automotive technology area, intelligent safety systems have been actively accomplished for drivers, passengers, and pedestrians. Also, many researches are focused on development of autonomous vehicles. This paper propose the application of LiDAR sensors, which takes major role in perceiving environment, terrain classification, obstacle data clustering method, and local map building for autonomous driving. Finally, based on these results, planning for lane change path that vehicle tracking possible were created and the reliability of path generation were experimented.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.5
• /
• pp.247-253
• /
• 2012

This paper presents sensor network based autonomous vehicle system using a proposed image processing algorithm. The proposed image processing algorithm consists of pre-processing and five-stage image processing: coordinate calculation, driving area decision, line segment calculation, steeling decision, and acceleration decision. We evaluate the performance of the proposed algorithm on both straight road and curved road. Experimental results indicate that the proposed algorithm works well for autonomous vehicles. However, control accuracy of the proposed algorithm decreases as speed is increasing.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.2
• /
• pp.144-155
• /
• 2019

One of the issues of the automotive industry today is autonomous driving vehicles. In order to achieve level 3 or higher as defined by SAE International, harmonization of autonomous driving technology and connected technology is essential. Current vehicles have new features such as autonomous driving, which not only increases the number of electrical components, but also the amount and complexity of software. As a result, the attack surface, which is the access point of attack, is widening, and software security vulnerabilities are also increasing. However, the reality is that the essential security requirements for vehicles are not defined. In this paper, based on real attacks and vulnerability cases and trends, we identify the assets in the in-vehicle network and derive the threats. We also defined the security requirements and derived essential security requirements that should be applied at least to the safety of the vehicle occupant through risk analysis.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.641-652
• /
• 2021

Drivers have willing to do secondary tasks in situations deemed safe autonomous driving. I studied that positive notifications for secure areas could improve situation awareness and driving performance after TOR(Take over request) in autonomous driving. Comparing TOR alert only and monitoring alert conditions, participants in the positive notification condition showed higher situation awareness and driving performance. Also, in emotional assessment, the positive notification condition showed higher positive evaluation than other conditions. Due to Covid-19, I designed experiments separate online with driving videos in experiment 1 and offline using a driving simulator in experiment 2. This study has implications that presented a different perspective on autonomous driving notification design.