• 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.

• Journal of the Society of Naval Architects of Korea
• /
• v.59 no.5
• /
• pp.314-322
• /
• 2022

During the shipbuilding process, many blocks are moved between shipyard workshops by block carrying vehicles called a transporter. Because block logistics management is one of the essential factors in enhancing productivity, it is necessary to manage block information with the transporter that moves it. Currently, because a large amount of data per day are collected from sensors attached to blocks and transporters via IoT infrastructure installed in shipyards, automated methods are needed to analyze them. Therefore, in this study, we developed an algorithm that can automatically match the transporter and the working block based on the GPS sensor data. By comparing the distance between the transporter and the blocks calculated from the Haversine formula, the block is found which is moved by the transporter. In this process, since the time of the measured data of moving objects is different, the time standard for calculating the distance must be determined. The developed algorithm was verified using actual data provided by the shipyard, and the correct result was confirmed with the distance based on the moving time of the transporter.

• Journal of Drive and Control
• /
• v.19 no.3
• /
• pp.9-15
• /
• 2022

This paper proposes a method for constructing and verifying datasets used in deep learning technology, to prevent safety accidents in automated construction machinery or autonomous vehicles. Although open datasets for developing image recognition technologies are challenging to meet requirements desired by users, this study proposes the interface of virtual simulators to facilitate the creation of training datasets desired by users. The pixel-level training image dataset was verified by creating scenarios, including various road types and objects in a virtual environment. Detecting an object from an image may interfere with the accurate path determination due to occlusion areas covered by another object. Thus, we construct a database, for developing an occlusion area detection algorithm in a virtual environment. Additionally, we present the possibility of its use as a deep learning dataset to calculate a grid map, that enables path search considering occlusion areas. Custom datasets are built using the RDBMS system.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.433-434
• /
• 2022

물류 시설에서 사람이 직접 물류를 입출고하는 방식이 일반적이다. 본 연구에서는 물류의 입출고를 인력의 소모 없이 보다 안전하고 효율적으로 하는 것을 전제로 하여 스마트 팩토리 산업에 사용되는 AGV 시스템에 물류 입출고 시스템을 접목하고자 한다. 본 논문은 기존의 인력의 소모와 산업재해 위험이 있는 물류 시설 근로 환경에 AGV를 이용, 인력의 소모를 줄여 물류 입출고 프로세스를 무인화하고자 "AGV 물류 자동화 시스템"을 제안한다. AGV 물류 자동화 시스템은 적외선 센서를 이용해 라인 트레이서를 구현하여 원하는 위치로 AGV를 이동시키고 각종 모터로 물품의 입출고 임무를 수행하도록 한다. 스마트폰의 물류 관리 어플리케이션을 통해 AGV의 제어와 물품의 재고 파악이 가능하도록 하여 물류관리의 효율성과 편의성을 증대시켰다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.131-132
• /
• 2022

We generate classifications and scenarios for intrusions based on 3D LiDAR Data. Research was conducted to analyze and diversify various actual intrusion cases to establish a system that can recognize objects and identify and guard data on intrusion. By generating and simulating basic scenarios for cars, people, animals, natural objects and etc, we create a classification scheme necessary to build and evaluate systems for intrusion. Based on the finally constructed scenario, we add variables for vehicles and surrounding objects to diversify scenarios, and lay the foundation for building accurate and automated alerting systems for future intrusions.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.79-91
• /
• 2024

Large warehouses are building automation systems to increase efficiency. However, small warehouses, military bases, and local stores are unable to introduce automated logistics systems due to lack of space and budget, and are handling tasks manually, failing to improve efficiency. To solve this problem, this study designed small loading and unloading equipment that can be mounted on transportation vehicles. The equipment can be controlled remotely and is automatically controlled from the point where pallets loaded with cargo are visible using real-time video from an attached camera. Cargo recognition and control command generation for automatic control are achieved through a newly designed deep learning model. This model is designed to be optimized for loading and unloading equipment and mission environments based on the YOLOv3 structure. The trained model recognized 10 types of palettes with different shapes and colors with an average accuracy of 100% and estimated the state with an accuracy of 99.47%. In addition, control commands were created to insert forks into pallets without failure in 14 scenarios assuming actual loading and unloading situations.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.224-239
• /
• 2023

C-ITS (Cooperative-Intelligent Transportation System) refers to user safety-oriented technology and systems that provide forward traffic situation information based on a two-way wireless communication technology between vehicles or between vehicles and infrastructure. Since the Daejeon-Sejong pilot project in 2016, the C-ITS infrastructure has been installed at various locations to provide C-ITS safety services through highway and local government demonstration projects. In this study, a methodology was developed to verify the effectiveness of the warning information using individual vehicle data collected through the Gwangju Metropolitan City C-ITS demonstration project. The analysis of the effectiveness was largely divided into driving behavior impact analysis and environmental analysis. Compliance analysis and driving safety evaluation were performed for the driving impact analysis. In addition, to supplement the inadequate collection of Probe Vehicle Data (PVD) collected during the C-ITS demonstration project, Digital Tacho Graph ( DTG ) data was additionally collected and used for effect analysis. The results of the compliance analysis showed that drivers displayed reduced driving behavior in response to warning information based on a sufficient number of valid samples. Also, the results of calculating and analyzing driving safety indicators, such as jerk and acceleration noise, revealed that driving safety was improved due to the provision of warning information.

• Journal of Korean Society of Transportation
• /
• v.33 no.2
• /
• pp.182-191
• /
• 2015

The Korean government introduced an automated speed enforcement system (ASES), which uses traffic enforcement cameras, to counteract safety issues that are caused by speeding. As the information of the traffic enforcement camera locations is provided to the drivers via navigation systems and mobile applications in a timely manner, drivers can avoid enforcement by momentarily diminishing their speeds only near the camera locations. To prevent drivers' evasional behavior and improve the effectiveness of ASES, section control, which enforces speeding vehicles by measuring their average travel speeds over a stretch of road and checking against the speed limit, has been recently implemented. In this study, Section Speed Enforcement Zone and Comparison Zone are compared in terms of traffic stream characteristics under free flow conditions. To this end, loop detector data were obtained from the three study sites and analyzed. The study results demonstrated that drivers maintain their speeds below the speed limit over the enforcement section with a lower variance of speeds.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.2
• /
• pp.195-211
• /
• 2023

For the commercialization For the commercialization of autonomous vehicles (AV), the operational design domain (ODD) of automated driving systems (ADS) is to be clearly defined. A common language and consistent format must be prepared so that AV-related stakeholders can understand ODD at the same level. Therefore, overseas countries are presenting a standardized ODD framework and developing scenarios that can evaluate ADS-specific functions based on ODD. However, ODD includes conditions reflecting the characteristics of each country, such as road environment, weather environment, and traffic environment. Thus, it is necessary to clearly understand the meaning of the items defined overseas and to harmonize them to reflect the specific domestic conditions. Therefore, in this study, domestic optimization of the ODD classification system was performed by analyzing the domestic driving environment based on international standards. The driving environment of currently operating self-driving car test districts (Sangam, Seoul, and Gwangju) was investigated using the developed domestic ODD items. Then, based on the results obtained, the ranges of the ODDs in each test district were determined and compared.

• Smart Media Journal
• /
• v.13 no.2
• /
• pp.52-61
• /
• 2024

In the shipyard, aerial images are acquired at regular intervals using Unmanned Aerial Vehicles (UAVs) for the management of external storage yards. These images are then investigated by humans to manage the status of the storage yards. This method requires a significant amount of time and manpower especially for large areas. In this paper, we propose an automated management technology based on a semantic segmentation foundation model to address these challenges and accurately assess the status of external storage yards. In addition, as there is insufficient publicly available dataset for external storage yards, we collected a small-scale dataset for external storage yards objects and equipment. Using this dataset, we fine-tune an object detector and extract initial object candidates. They are utilized as prompts for the Segment Anything Model(SAM) to obtain precise semantic segmentation results. Furthermore, to facilitate continuous storage yards dataset collection, we propose a training data generation pipeline using SAM. Our proposed method has achieved 4.00%p higher performance compared to those of previous semantic segmentation methods on average. Specifically, our method has achieved 5.08% higher performance than that of SegFormer.