• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.1
• /
• pp.15-26
• /
• 2023

In this study, an end-effector robot which is a two-axis delta robot type for upper-limb rehabilitation is designed. It is not only rehabilitation functions that has designed robot but also mechanical and electrical safety devices were constructed to ensure patient safety. By constructing the two-axis delta robot is combined with an LM guide, the operating range and rigidity required for rehabilitation were secured. The electrical safety system which is required for the medical robot was designed, and a safety strategy was established to ensure patient safety and it is applied in the integrated safety circuit. The safety is considered in whole design process from the robot's mechanical design to the electric control unit.

• Journal of Gastric Cancer
• /
• v.14 no.3
• /
• pp.211-214
• /
• 2014

We report our experience of a concurrent robot assisted distal gastrectomy and partial nephrectomy for synchronous early gastric cancer and renal cell carcinoma. A 55-year-old female patient was diagnosed with early gastric cancer on screening endoscopy. Abdominal computed tomography showed an incidental right renal cell carcinoma. Robot assisted distal gastrectomy was performed, followed by partial nephrectomy. The final pathological examination showed signet ring cell carcinoma within the lamina propria and renal cell carcinoma with negative resection margins. The patient showed no evidence of recurrence at 6-months. A robot-assisted combined operation could be a treatment option for early stages of synchronous malignancies.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.3
• /
• pp.1-10
• /
• 2011

In this paper, we propose a face detection method for medical service robot. The proposed method is robust in complex background and light. Our method is performed by three steps. Firstly the background is eliminated using mean shift algorithm. Thereafter, based on color space, face is extracted. Finally the object is extracted using Haar-like feature method. To assess the effectiveness of the proposed system, it was tested and experimental results show that the proposed method is applicable for medical service robot.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.9
• /
• pp.21-31
• /
• 2000

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.349-350
• /
• 2011

• Journal of Mechanical Science and Technology
• /
• v.18 no.11
• /
• pp.1949-1960
• /
• 2004

This paper presents a robot system developed for medical purpose. A 6-degree-of-freedom robot was introduced for physical exercise and rehabilitation. This system was proposed for stroke patients or patients who cannot use one of their arms or legs. The robot system exercises the hemiplegic part based on the motion of normal part of a patient. Kinematic studies on the human body and robot were applied to develop the robotic rehabilitation exercise system. A clamp which acts as an end effector of the robot to hold a patient was designed and applied to the robot to guarantee the safety of patients. The proposed robotic rehabilitation system was verified by simulations and experiments on arm (elbow and shoulder) motion. Patients are expected to be able to exercise various motions by themselves with the proposed robotic rehabilitation system.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.15-20
• /
• 2023

Machine learning is comprised of supervised learning, unsupervised learning and reinforcement learning as the type of data and processing mechanism. In this paper, as input and output are unclear and it is difficult to apply the concrete modeling mathematically, reinforcement learning method are applied for crawling robot in this paper. Especially, Q-Learning is the most effective learning technique in model free reinforcement learning. This paper presents a method to implement a crawling robot that is operated by finding the most optimal crawling method through trial and error in a dynamic environment using a Q-learning algorithm. The goal is to perform reinforcement learning to find the optimal two motor angle for the best performance, and finally to maintain the most mature and stable motion about EV3 Crawling robot. In this paper, for the production of the crawling robot, it was produced using Lego Mindstorms with two motors, an ultrasonic sensor, a brick and switches, and EV3 Classroom SW are used for this implementation. By repeating 3 times learning, total 60 data are acquired, and two motor angles vs. crawling distance graph are plotted for the more understanding. Applying the Q-learning reinforcement learning algorithm, it was confirmed that the crawling robot found the optimal motor angle and operated with trained learning, and learn to know the direction for the future research.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.6
• /
• pp.1245-1250
• /
• 2011

In this paper, we designed efficient reception system using service robot based on the RFID(Radio Frequency Identification) and HL7(Health Level 7) Protocol. The proposed system offer a paramedic the medical information of the patient, and the patients can receive on a much simpler scale than previously through stable and quick information exchange by RFID and HL7. In addition, We considered environment of medical treatment and designed and implemented standard HL7 message structure. This system was implemented service robots to reception of medical treatment. Furthermore, we have plan to develop bio-sensor which can measure blood pressure, body temperature, etc and interface with robot system by HL7.

• Journal of Biomedical Engineering Research
• /
• v.24 no.4
• /
• pp.309-318
• /
• 2003

In this paper a 6 degree-of-freedom robot was studied for medical purpose. In the past the robot used for industry field was utilized for medical robot but in these days the robot used for rehabilitation. welfare, and service. This system was Proposed for a stroke patient or a patient who can not use one arm. A master-slave system was constructed to exercise either paralysis or abnormal arm using normal arms movement. Study on the human body motion result was applied to calculate a movement range of humans elbow and shoulder. In addition, a force-torque sensor is applied to estimate the rehabilitation extent of the patient in the slave robot. Therefore, the stability of the rehabilitation robot could be improved. By using the rehabilitation robot, the Patient could exercise by himself without any assistance In conclusion. the proposed system and control algorithm were verified by computer simulation and system experiment.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2660-2664
• /
• 2003

In this study, the concept of autonomous mobility is applied to a medical service robot. The aim of the development of the service robot is for the elderly assisting walking rehabilitation. This study aims that the service robot design parameter is proposed in ergonomic view. The walking assistant path pattern is derived from analyzing the elderly gait analysis. A lever is installed in the AMR in order to measure the pulling force and the leading force of the elderly. A lever mechanism is applied for walking assistant service of the AMR. This lever is designed for measuring the leading force of the elderly. The elderly adjusts the velocity of the robot by applying force to the lever. The action scope and the service mechanism of the robot are developed for considering and analyzing the elderly action patterns. The ergonomic design parameters, that is, dimensions, action scope and working space are determined based on the elderly moving scope. The gait information is acquired by measuring the guide lever force by load cells and working pattern by the electromyography signal.