• Journal of Multimedia Information System
• /
• 제7권1호
• /
• pp.41-44
• /
• 2020

In autonomous driving, object recognition based on machine learning is one of the core software technologies. In particular, the object recognition using deep learning becomes an essential element for autonomous driving software to operate. In this paper, we introduce a drivable area detection method based on Region-based CNN model to support autonomous driving. To effectively detect the drivable area, we used the BDD dataset for model training and demonstrated its effectiveness. As a result, our R-CNN model using BDD datasets showed interesting results in training and testing for detection of drivable areas.

• 품질경영학회지
• /
• 제46권4호
• /
• pp.1001-1014
• /
• 2018

Purpose: Autonomous driving cars, which are often represent the new convergence product, have been researched since the early years of 1900 but their safety assurance policies are yet to be implemented for real world practices. The primary purpose of this paper is to propose a modular concept based on which a safety assurance system can be designed and implemented for operating autonomous driving cars. Methods: We combine a set of key attributes of CE mark (European Assurance standard), E-Mark (Automobile safety assurance system), and A-SPICE (Automobile software assurance standard) into a modular approach. Results: Autonomous vehicles are emphasizing software safety, but there is no integrated safety certification standard for products and software. As such, there is complexity in the product and software safety certification process during the development phase. Using the concept of module, we were able to come up with an integrated safety certification system of product and software for practical uses in the future. Conclusion: Through the modular concept, both international and domestic standards policy stakeholders are expected to consider a new structure that can help the autonomous driving industries expedite their commercialization for the technology advanced market in the era of Industry 4.0.

• 대한임베디드공학회논문지
• /
• 제18권5호
• /
• pp.249-257
• /
• 2023

This paper discusses the increasing need for autonomous delivery robots due to the current growth in the delivery market, rising delivery fees, high costs of hiring delivery personnel, and the need for contactless services. Additionally, the cost of hardware and complex software systems required to build and operate autonomous delivery robots is high. To provide a low-cost alternative to this, this paper proposes a autonomous delivery robot platform using a low-cost sensor combination of 2D LIDAR, depth camera and tracking camera to replace the existing expensive 3D LIDAR. The proposed robot was developed using the RTAB-Map SLAM open source package for 2D mapping and overcomes the limitations of low-cost sensors by using the convex hull algorithm. The paper details the hardware and software configuration of the robot and presents the results of driving experiments. The proposed platform has significant potential for various industries, including the delivery and other industries.

• 한국ITS학회 논문지
• /
• 제20권6호
• /
• pp.242-263
• /
• 2021

본 논문은 자율주행 알고리즘 개발을 위한 저비용 드라이빙 시뮬레이터 구축 방법을 소개한다. 이는 물리엔진을 적용한 상용게임 소프트웨어인 GTA V를 활용하여 구현되며 자율주행 시스템에 필요한 다양한 센서 출력값 및 데이터를 에뮬레이션하는 기능을 내장한다. 이를 위해 GTA V 내부 데이터를 취득할 수 있는 Script Hook V의 NF를 활용하여 GT 데이터를 취득하고, 이를 활용하여 다양한 자율주행용 센서 데이터를 생성한다. 본문에서는 설계된 드라이빙 시뮬레이터의 전반적인 기능들을 소개하며, 개별 기능에 대한 검증을 수행한다. 자율주행 알고리즘 개발 환경 구축을 위해 게임 엔진 내부 메모리 접근을 통한 GT 데이터를 취득하는 과정을 설명하고, 에뮬레이션된 센서값을 처리 및 활용하여 인공 신경망 학습 및 성능평가에 적용 가능한 예시를 제시한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3523-3543
• /
• 2022

Autonomous vehicles are gradually being regarded as the mainstream trend of future development of the automobile industry. Autonomous driving networks generate many intensive and delay-sensitive computing tasks. The storage space, computing power, and battery capacity of autonomous vehicle terminals cannot meet the resource requirements of the tasks. In this paper, we focus on the task scheduling problem of autonomous driving in software-defined edge networks. By analyzing the intensive and delay-sensitive computing tasks of autonomous vehicles, we propose an emotion model that is related to task urgency and changes with execution time and propose an optimal base station (BS) task scheduling (OBSTS) algorithm. Task sentiment is an important factor that changes with the length of time that computing tasks with different urgency levels remain in the queue. The algorithm uses task sentiment as a performance indicator to measure task scheduling. Experimental results show that the OBSTS algorithm can more effectively meet the intensive and delay-sensitive requirements of vehicle terminals for network resources and improve user service experience.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권2호
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1223-1237
• /
• 2024

Autonomous vehicles use onboard sensors to sense the surrounding environment. In complex autonomous driving scenarios, the detection and recognition capabilities are constrained, which may result in serious accidents. An efficient way to enhance the detection and recognition capabilities is establishing collaborations with the neighbor vehicles. However, the collaborations introduce additional challenges in terms of the data heterogeneity, communication cost, and data privacy. In this paper, a novel personalized federated learning framework is proposed for addressing the challenges and enabling efficient collaborations in autonomous driving environment. For obtaining a global model, vehicles perform local training and transmit logits to a central unit instead of the entire model, and thus the communication cost is minimized, and the data privacy is protected. Then, the inference similarity is derived for capturing the characteristics of data heterogeneity. The vehicles are divided into clusters based on the inference similarity and a weighted aggregation is performed within a cluster. Finally, the vehicles download the corresponding aggregated global model and train a personalized model which is personalized for the cluster that has similar data distribution, so that accuracy is not affected by heterogeneous data. Experimental results demonstrate significant advantages of our proposed method in improving the efficiency of collaborative perception and reducing communication cost.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• 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.

• 디지털산업정보학회논문지
• /
• 제17권4호
• /
• pp.31-42
• /
• 2021

In the modern era, radio wave analysis is necessary for various fields of engineering, and interpretation of this is also indispensable. Self-driving cars need multiple different electronic components, and thus accurate and fast electromagnetic simulator for this kind of complex radio environment is required for self-driving simulations. Accordingly, the demand for self-driving simulators as well as existing electromagnetic analysis software has increased. This paper briefly describes the characteristics of numerical analysis techniques for electromagnetic analysis, self-driving simulation software, and conventional electromagnetic simulation software and also summarizes the characteristics of each software. Finally, the verification of the result from in-house code compared to HFSS is demonstrated.

• 자동차안전학회지
• /
• 제14권2호
• /
• pp.26-38
• /
• 2022

This paper proposes multiple RLS and actuator performance index-based adaptive actuator fault-tolerant control and detection algorithms for longitudinal autonomous driving. The proposed algorithm computes the desired acceleration using feedback law for longitudinal autonomous driving. When actuator fault or performance degradation exists, it is designed that the desired acceleration is adjusted with the calculated feedback gains based on multiple RLS and gradient descent method for fault-tolerant control. In order to define the performance index, the error between the desired and actual accelerations is used. The window-based weighted error standard deviation is computed with the design parameters. Fault level decision algorithm that can represent three fault levels such as normal, warning, emergency levels is proposed in this study. Performance evaluation under various driving scenarios with actuator fault was conducted based on co-simulation of Matlab/Simulink and commercial software (CarMaker).