• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.1136-1139
• /
• 2021

쇼핑카트 부착 모듈형 로봇 'Cart-Rider'는 어드미턴스 제어를 통한 사용자의 힘 보조 기능, 딥러닝을 활용한 네비게이션 기능, GPS 를 활용한 도난 방지 기능을 제공하는 로봇으로 대형 마트에서 발생하는 안전사고 및 쇼핑카트 도난을 예방하는 동시에 사용자에게 편의성을 제공하는 로봇이다. 또한 여러 대를 겹쳐서 보관하는 기존의 카트 시스템을 유지하고 탈부착이 용이하도록 하드웨어를 제작하여 환경에 영향을 주지 않고 유지 및 보수가 용이하도록 제작했다.

• Journal of KIISE:Software and Applications
• /
• v.37 no.5
• /
• pp.363-369
• /
• 2010

Demonstration-based learning has the advantage that a user can easily teach his/her robot new task knowledge just by demonstrating directly how to perform the task. However, many previous demonstration-based learning techniques used a kind of attribute-value vector model to represent their state spaces and policies. Due to the limitation of this model, they suffered from both low efficiency of the learning process and low reusability of the learned policy. In this paper, we present a new demonstration-based learning method, in which the relational model is adopted in place of the attribute-value model. Applying the relational instance-based learning to the training examples extracted from the records of the user demonstrations, the method derives a relational instance-based policy which can be easily utilized for other similar tasks in the same domain. A relational policy maps a context, represented as a pair of (state, goal), to a corresponding action to be executed. In this paper, we give a detail explanation of our demonstration-based relational policy learning method, and then analyze the effectiveness of our learning method through some experiments using a robot simulator.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.11
• /
• pp.1113-1121
• /
• 2015

In this study, we have focused on the design of a controller and an operating program for the operation of the hydraulic actuators used in a shaker. To control the motion of the shaker accurately, the position of each hydraulic cylinder should be controlled precisely even under an uncertain environment. For this purpose, we have suggested a control algorithm using an FRF (frequency response function) based control which senses the behavior of the actuator in advance, calculates a transfer function through the system identification method, and provides the final control input. The experimental results on the performance of this system were compared with that of a simple PID control algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2313-2321
• /
• 2014

A concentration meter is widely used at purification plants, sewage treatment plants and waste water treatment plants to sort and transfer high concentration sludge and to control the amount of chemical input. This study has been prepared for improving efficiency of operation on sludge processes and to establish a basic for factory automation by accuracy improvement and problem solution of sludge concentration meter. The concentration meter's accuracy and stability is improved by applying multi-beam sensors and minimum deviation linear average filtering. Furthermore maintenance without cut-off of water in sludge operation is possible by detachable sensors. The performance of multi-beam concentration meter has been variously verified by the pilot plant experiment.

• Archives of Plastic Surgery
• /
• v.49 no.1
• /
• pp.29-33
• /
• 2022

The application of minimal invasive mastectomy has allowed surgeons to perform nipples-paring mastectomy via a shorter, inconspicuous incision under clear vision and with more precise hemostasis. However, it poses new challenges in microsurgical breast reconstruction, such as vascular anastomosis and flap insetting, which are considerably more difficult to perform through the shorter incision on the lateral breast border. We propose an innovative technique of transcutaneous medial fixation sutures to help in flap insetting and creating and maintaining the medial breast border. The sutures are placed after mastectomy and before flap transfer. Three 4-0 nylon suture loops are placed transcutaneously and into the pocket at the markings of the preferred lower medial border of the reconstructed breast. After microvascular anastomosis and temporary shaping of the flap on top of the mastectomy skin, the three corresponding points for the sutures are identified. The three nylon loops are then sutured to the dermis of the corresponding medial point of the flap. The flap is placed into the pocket by a simultaneous gentle pull on the three sutures and a combined lateral push. The stitches are then tied and buried after completion of flap inset.

• Journal of Korean Society for Quality Management
• /
• v.51 no.3
• /
• pp.381-401
• /
• 2023

Purpose: The purpose of this study was to understand the perception of medical staff to propose an infected patient transport robot as a means of responding to infectious diseases. Methods: The data collected through the survey was analyzed through AHP analysis. The measurement tools used in this study were derived through the SERVQUAL model and Focus Group Interview(FGI), and consisted of four detailed questions for each of five classes: tangible, reliability, responsiveness, assurance, and empathy. Results: As a result of the study, there are concerns about risk factors that may occur in areas where medical staff intervention is minimized. Above all, we confirmed the consensus that safety should be the top priority during the process of robots to transport patients. In particular, highlighted were the resolution of device errors that may occur during the process for transporting patients and easy provision of the first aid. Additionally, the ability to monitor patients and suppress infection factors turned out to be important, which was directly related to the simplification of the role of medical staff and work efficiency. Conclusion: As one of the means of effectively controlling infectious diseases in a pandemic situation, a robot to transport the infected patient was considered. However, in order to commercialize this, specific verification of the safety of medical staff and patients is needed, and empirical data on providing the first aid, patient monitoring, and infection factor suppression should be presented.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.329-331
• /
• 2018

In this paper, we propose a monitoring system that starts with the supply of raw materials for threading, is processed into a lathe machine, and checks for defects of the product are automatically performed by the robot with Smart Factory technology through assembly and disassembly. Completion check according to the production instruction quantity and production instruction is made by checking the production status according to whether or not the raw material is worn by the displacement sensor, and checking the pitch and the contour of the processed female and male to determine OK and NG. The robotic system acts as a relay for loading and unloading of raw materials, pallet transfer, and overall process, and it acts as an intermediary for organically driving. The location information of the threaded products is collected by using the non-contact wireless tag and the energy saving system Production efficiency and utilization rate were checked. The environmental sensor collects the air-conditioning environment data (temperature, humidity), measures the temperature and humidity accurately, and checks the quality of product processing. It monitors and monitors the driving hazard level environment (overheating, humidity) of the product. Controls for CNC and robot module PLC as a heterogeneous system.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1137-1144
• /
• 2022

In this study, an artificial intelligence(AI) was developed to help with facial expression practice in order to express emotions. The developed AI used multimodal inputs consisting of sentences and facial images for deep neural networks (DNNs). The DNNs calculated similarities between the emotions predicted by the sentences and the emotions predicted by facial images. The user practiced facial expressions based on the situation given by sentences, and the AI provided the user with numerical feedback based on the similarity between the emotion predicted by sentence and the emotion predicted by facial expression. ResNet34 structure was trained on FER2013 public data to predict emotions from facial images. To predict emotions in sentences, KoBERT model was trained in transfer learning manner using the conversational speech dataset for emotion classification opened to the public by AIHub. The DNN that predicts emotions from the facial images demonstrated 65% accuracy, which is comparable to human emotional classification ability. The DNN that predicts emotions from the sentences achieved 90% accuracy. The performance of the developed AI was evaluated through experiments with changing facial expressions in which an ordinary person was participated.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.9
• /
• pp.841-851
• /
• 2014

Wireless technologies sharing the same frequency band and operating in the same environment often interfere with each other, causing severe decrease in performance. In this paper, we propose a algorithm based on traffic scheduling techniques that mitigate interference between different wireless systems operating in the 2.4-GHz industrial, medical, and scientific band. In particular, we consider IEEE 802.11 wireless local area networks (WLANs) and Bluetooth data transfer, showing that the proposed algorithms can work when the two systems are able to exchange information as well as when they operate independently of one another. Results indicate that the proposed algorithm remarkably mitigate the interference between the WLAN and Bluetooth technologies at the expense of a small additional delay in the data transfer.

• Journal of Biosystems Engineering
• /
• v.34 no.5
• /
• pp.305-314
• /
• 2009

The purpose of this paper was to design an effective control system of 1-axis exciter for a seat vibration test of agricultural tractors using MATLAB simulation. The developed simulation model was composed with a hydraulic pump, a hydraulic servo valve, a hydraulic cylinder and load system. Also it was verified by comparing the simulation results with experimental results of actual control system in order to optimize the control performance. And in order to improve its control performance, the designed PID controller in this research was tuned using Ziegler-Nichols 2nd law and zero's moving method of PID controller's transfer function. As the result of these research, the developed position control system was able to control the system's position accurately within 5% errors.