• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.157-163
• /
• 2020

Recently, fine dust has been known to cause cardiovascular diseases here, raising interest in ways to reduce emissions by efficiently using fuel from cars that cause air pollution. Accordingly, a driving assistance system was developed to save fuel by eco-driving and improve the driver's bad driving habits. The system was developed using raspberry pi, arduino and Android. Using RPM, speed, fuel injection information obtained from OBD-II, and gyro-sensor values, Fuel-Cut is induced to create an optimal inertial driving environment. It also provides various information system such as weather, driving environment, and preventing drowsy driving through GUI and voice recognition functions. It is possible to check driving records and vehicle fault information using Android application and has low overhead for message transmission using MQTT protocol optimized for IoT environment.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.

• Journal of Biomedical Engineering Research
• /
• v.18 no.4
• /
• pp.447-456
• /
• 1997

When the disabled is operating a rehabilitation assisting system with a joystick by himself, unlike in the case of a normal person, tremor with joystick control or instant miscontrol can often occur. If these misoperations should be directly relayed to the system, shaking or malfunction of the mobile rehabilitation assisting system might be the result. The safety of the disabled is of prime concern. To solve this problem, that is, to prevent the miscontrol of the disabled operator and avoid crashes into his or her surroundings, we propose the force-reflection locomotion algorithm with the joystick. This method uses ultrasonic sensors to measure the distance between the object and mobile robot. Based on the reception of sensory data, the necessary torque is applied via the joystick to the attatched motor. To confirm the effectiveness of the proposed method, the subjects on the reflected force by the dynamic characteristics of the joystick and the reflected force by the distance information are tested Even though there are some differences in human dexterity, we confirmed the fact that the information from the obstacles was relayed to the operator via the joystick and resulted in an improved operational performance and safety level with regard to those obstacles.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.4
• /
• pp.68-80
• /
• 2016

This study proposes the traffic prediction and optimal traffic control system based on cell transmission model and genetic algorithm in cloud environment. The proposed prediction and control system consists of four parts. 1) Data preprocessing module detects and imputes the corrupted data and missing data points. 2) Data-driven traffic prediction module predicts the future traffic state using Multi-level K-Nearest Neighbor (MK-NN) Algorithm with stored historical data in SQL database. 3) Online traffic simulation module simulates the future traffic state in various situations including accident, road work, and extreme weather condition with predicted traffic data by MK-NN. 4) Optimal road control module produces the control strategy for large road network with cell transmission model and genetic algorithm. The results show that proposed system can effectively reduce the Vehicle Hours Traveled upto 60%.

• Journal of Biomedical Engineering Research
• /
• v.16 no.4
• /
• pp.543-554
• /
• 1995

This paper describes the improvement of driving stability and the control system for INMEL-VII which is motorized manual wheelchair to satisfy requirements of the disabled The INMEL-VI was based on high maneuverability of the omnidirection drive and safety But the results of field tests about two years showed some problems to the disabled in daily life such as driving stability, Pm switching noise, and rotation of motor without driving command on negative slope. To solve the problems due to an increased DC motor power and applied to direct connection method in INMEL- VII. It improved the driving circuits and set switching frequency to 5KHz to eliminate the switching noise caused by PWM control of DC motor, As compare with the INMEL-VI, INMEL-VII is improved in driving stability by transfer the weight center to forward. The results of field testing proved the improvement of the driving stability and software algorithm It has been estimated to have a hlgh practical use for powered walking aids to the disabled's daily life.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.544-549
• /
• 2006

This research is to introduce about Judgment System for Intelligent Movement(JSIM) that can perform assistance work of human brain. JSIM can order autonomous command and also it can be directly controlled by user. This research assumes that control object is limited to Mobile Robot(MR) Mobile robot offers image and ultrasonic sensor information to user carrying JSIM and it performs guide to user. JSIM having PDA and Sensor-box controls velocity and direction of the mobile robot by soft-computing method that inputs user's command and information that is obtained to mobile robot. Also it controls mobile robot to achieve various movement. This paper introduces wearable JSIM that communicates with around devices and that can do intelligent judgment. To verify the possibility of the proposed system, in real environment, the simulation of control and application problem lot mobile robot will be introduced. Intelligent algorithm in the proposed system is generated by mixed hierarchical fuzzy and neural network.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.191-193
• /
• 2016

후방 램프를 이용하는 기존의 차량 검출 기법들은 주로 색상 정보를 활용한다. 그러나 조도가 낮은 야간 환경의 특성상 색상 정보를 온전히 활용할 수 없는 경우가 빈번하게 발생한다. 이를 해결하기 위해 본 논문에서는 야간 환경에서 후방 램프의 밝기 값만을 이용해 차량을 검출한다. 일반적으로 후방 램프를 검출하기 위해 색상 정보와 밝기 값을 이용해 이진화를 하게 되는데, 본 논문에서는 밝기 값을 이용해 톤 매핑 과정을 수행하여 후방 램프의 모양을 보존한다. 밝기 값 만을 이용하기 때문에 오검출이 증가하게 되는데 이는 후방 램프에 대한 조건을 알고리즘에 적용함으로써 해결한다. 이에 더해 추적 알고리즘을 적용하여 남아있는 오검출을 제거한다. 이러한 과정은 모두 실시간으로 이루어지기 때문에 최근 활발히 연구되고 있는 자동 주행 시스템이나 주행 보조 시스템 등에 활용 될 수 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.98-101
• /
• 2002

기존의 이동로봇 시스템은 완전한 자율주행이 주된 목표였으며 이때 영상정보는 단지 모니터링을 하는 보조적인 수단으로 사용되었다. 이에 따라 이동로봇의 자체 기능이 점차 고도화되는 방향으로 연구가 진행되었고, 제작비 또한 함께 상승하게 되었다. 그러나 구동만이 목적인 저렴한 이동로봇 시스템을 조작자가 원격 제어하는 것 또한 중요한 분야 중 하나이다. 이때 원격제어에 사용되는 신호로는 카메라에 의한 영상정보와 초음파 센서 등에 의한 거리정보를 주로 사용하게 된다. 그러나 영상정보는 3차원의 입체적 정보를 제공하는 데에는 부적절하기 때문에 초음파 센서를 이용한 거리정보가 매우 유용하게 된다. 본 논문에서는 초음파 센서의 정보를 이용한 원격제어용 힘 반향 조이스틱을 개발하였다. 힘 반향 알고리즘은 하나의 식으로 표현하기 곤란하므로 전문가 시스템의 구현이 매우 필요한 분야이다. 따라서 퍼지 논리를 사용하여 생성한 힘 반향 알고리즘을 이동로봇 원격제어에 사용함으로써 조작자가 이동로봇 주변환경을 쉽게 인식하여 이동로봇을 안전하게 주행할 수 있도록 하였다.

• Information and Communications Magazine
• /
• v.34 no.5
• /
• pp.3-9
• /
• 2017

운전자 보조 시스템이나 자율 주행 자동차 기술의 등장 등 자동차 산업이 고도화됨에 따라 차량에 탑재되는 전기/전자 시스템의 수와 시스템의 복잡도가 점차 증가하고 있다. 특히 주행 중심에서 안전 중심으로 산업의 패러다임이 변화함에 따라 전기/전자 시스템의 오작동으로 인한 사고를 방지하는 것이 중요 이슈로 부각되었고, 이를 충족하기 위해 지난2011년 자동차 기능안전 국제 표준인 ISO 26262가 제정되었다. ISO 26262:2011은 총 10개의 Part로 구성되어 있으며, 개발 초기단계부터 생산 및 운영, 폐기단계까지 준수해야 할 안전 관련 요구사항을 제시하고 있다. OEM을 비롯한 많은 협력 업체들은 이미 이를 준수하여 국내외 완성차 업체에 대응하고 있으며, 더 나아가 2018년에 예정된 ISO 26262 2차 개정을 미리 준비하고 있다. 본 고에서는 ISO 26262:2011의 등장 배경과 개념에 대해 설명하고, ISO 26262:2011의 효과적인 대응을 위한 수행 방안을 Part 3 개념 단계부터 Part 6 소프트웨어 수준의 제품 개발 단계까지 주요 핵심 수행 활동을 중심으로 소개한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.149-155
• /
• 2020

The Korea Highway Traffic Authority provides statistics that analyze the causes of traffic accidents that occurred since 2015 using the Traffic Accident Analysis System (TAAS). it was reported Through TAAS that the driver's forward carelessness was the main cause of traffic accidents in 2018. As statistics on the cause of traffic accidents, 51.2 percent used mobile phones and watched DMB while driving, 14 percent did not secure safe distance, and 3.6 percent violated their duty to protect pedestrians, representing a total of 68.8 percent. In this paper, we propose a system that has improved the advanced driver assistance system ADAS (Advanced Driver Assistance Systems) by utilizing CNN (Convolutional Neural Network) among the algorithms of Deep Learning. The proposed system learns a model that classifies the movement of the driver's face and eyes using Conv2D techniques which are mainly used for Image processing, while recognizing and detecting objects around the vehicle with cameras attached to the front of the vehicle to recognize the driving environment. Then, using the learned visual steering model and driving environment data, the hazard is classified and detected in three stages, depending on the driver's view and driving environment to assist the driver with the forward and blind spots.