• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.2
• /
• pp.121-127
• /
• 2007

Frequent occurrences of a fire cause tremendous loss of human lives and their property. Recently, in order to cope with such catastrophic accidents, researches on fire-fighting robots are carried out in developed countries. Under the dangerous situations, it is sometimes impossible for fire-fighting men to access the firing place because of explosive materials, smoke, high temperature and so on. In such an environment, fire-fighting robots can be useful to extinguish the fire. It is usually very dangerous place where fire-fighting robots operate. Hence, these robots should be controlled by remote users who are for away from the firing place exploiting remote communication systems. This paper considers the communication systems between fire-fighting robots and remote users. The communication systems consist of two parts; digital packet communication systems and analog image communication systems. Digital packet communication systems transfer data packets in order to control fire-fighting robots and to check the state of the fire-fighting robots. Remote users watch the video around the fire-fighting robots by exploiting the analog image communication systems. In the future, the more prosperous the commercial communication network systems will be, the more evolved the communication systems for fire-fighting robots are.

• Proceedings of the Safety Management and Science Conference
• /
• 2013.04a
• /
• pp.471-484
• /
• 2013

Large and complicated firefighting environment is accelerating in the early activities in the field of fire officials at the time limit situation leads to people's lives and property damage, as well as the loss of the Fire Service. Therefore, the state-of-the-art technology that can respond to rapidly changing fire environment urgently in the field of fire fighting have been introduced should be utilized. These intelligent firefighting robots build daegukmin firefighting safety net that can be used when. Other advanced technology industries, the most effective ways that can be introduced into the firefighting shall be provided in the current situation of the industry's initial firefighting robots.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.4
• /
• pp.452-459
• /
• 2018

Conventional fire fighting robots are controlled by a remote control to monitor the fire scene or to suppress the fire. However, this method has a problem that it takes a long time to prepare robot and input it to fire place in the golden time after the fire, so that it can not sufficiently serve as a fire fighting robot. Using the autonomous driving fire monitoring robot, when a fire signal is generated, in conjunction with a fire receiver a moving robot takes a video of the fire scene and delivers the image to the fire department, so that the fire fighter can decide if it is real fire or not. Thereby it is possible to prevent a sudden spread of an accident by providing a quick judgment opportunity and at the same time suppressing the fire early. In this paper, we propose an architecture of the autonomous mobile fire monitoring robot and the communication protocol required for the robot to work with the fire receiver. A communication protocol is designed to control multiple fire monitoring robots in real time, and a communication with a fire receiver is designed as a hierarchical network to serve as an interface of an Ethernet network using wireless Wi-Fi. The fire monitoring robot and the wireless communication of the fire receiving period are implemented and the effectiveness of the operation is confirmed through the field test.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2007.11a
• /
• pp.219-224
• /
• 2007

• Fire Science and Engineering
• /
• v.29 no.6
• /
• pp.109-118
• /
• 2015

Recently, three kinds of search robot prototypes were developed to assume the role of fire fighters for search and rescue missions in special disaster areas with high heat, smoke, toxic gases, or radioactivity. To accomplish search missions, these robots should be able to endure heat, overcome various obstacles, suppress fires, and see through dense smoke. This study investigated the heat resistance, practicality, and fire fighting capacity of these robots. The results show that the small and middle-sized robots were resistant to surrounding temperatures of $100{\sim}200^{\circ}C$, and the fire-fighter-riding robot could endure up to $500^{\circ}C$ for half an hour. The fire-fighter-riding robot showed excellent extinguishing performance on an A-10 class fire model, which was extinguished within 3 min. The robots also showed various capacities for overcoming obstacles and are expected to play an active role in various special disaster areas.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.2
• /
• pp.108-113
• /
• 2007

The robot introduced in this paper is the Fire-Extinguishing Rescue Robot for indoor work which is considered to be a part of the Operation for Future Developmental Power. It is briefly introduced about the background of how we began this project, our goals, where we are today and what we would like to achieve from now on. Main contents include introduction to the equipments for Fire-Extinguishing Rescue robots that have been developed in advanced countries and the compositional concept of the developmental process, the GUI schematic, searching methods for fire inside a house, mechanical schematic and the present conditions of how the core technologies are developing through.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2007.11a
• /
• pp.213-218
• /
• 2007

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.3
• /
• pp.1-9
• /
• 2019

The image obtained from systems such as autonomous driving cars or fire-fighting robots often suffer from several degradation such as noise, motion blur, and compression artifact due to multiple factor. It is difficult to apply image recognition to these degraded images, then the image restoration is essential. However, these systems cannot recognize what kind of degradation and thus there are difficulty restoring the images. In this paper, we propose the deep neural network, which restore natural images from images degraded in several ways such as noise, blur and JPEG compression in situations where the distortion applied to images is not recognized. We adopt the channel attention modules and skip connections in the proposed method, which makes the network focus on valuable information to image restoration. The proposed method is simpler to train than other methods, and experimental results show that the proposed method outperforms existing state-of-the-art methods.