• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.221-228
• /
• 2022

With the application of artificial intelligence technology, robots can provide efficient services in real life. Unlike industrial manipulators that do simple repetitive work, this study presented design methods of 6 degree of freedom robot arm and intelligent object search and movement methods for use alone or in collaboration with no place restrictions in the service robot field and verified performance. Using a depth camera and deep learning in the ROS environment of the embedded board included in the robot arm, the robot arm detects objects and moves to the object area through inverse kinematics analysis. In addition, when contacting an object, it was possible to accurately hold and move the object through the analysis of the force sensor value. To verify the performance of the manufactured robot arm, experiments were conducted on accurate positioning of objects through deep learning and image processing, motor control, and object separation, and finally robot arm was tested to separate various cups commonly used in cafes to check whether they actually operate.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.237-242
• /
• 2023

Research on high-performance walking robots is being actively conducted, and quadruped walking robots are receiving a lot of attention due to their excellent mobility and adaptability on uneven terrain, but they are difficult to introduce and utilize due to high cost. In this paper, to increase utilization by applying intelligent functions to a low-cost quadruped robot, we present a method of improving uneven terrain overcoming ability by mounting IMU and reinforcement learning on embedded board and automatically detecting objects using camera and deep learning. The robot consists of the legs of a quadruped mammal, and each leg has three degrees of freedom. We train complex terrain in simulation environments with designed 3D model and apply it to real robot. Through the application of this research method, it was confirmed that there was no significant difference in walking ability between flat and non-flat terrain, and the behavior of performing person detection in real time under limited experimental conditions was confirmed.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.1
• /
• pp.507-513
• /
• 2020

This paper aims to design and implement a robot that will help teach children living habits and English conversation education in dual-income families using the open platform robot Q.bo one based on raspberry pi3 of a single board computer. The first function of life habit formation is to help children to wash their hands, to brush their teeth, homework and sleep regularly. The child is then photographed listening to the notification and acting so that the parent can identify and provide feedback. The second basic conversation education feature uses Google's DialogFlow to help children learn English naturally through simple English conversation through the robot. The two-functioning robot allows children from working families to feel secure by printing their parents' voices even when they are not at home. At the same time, it allows them to get into basic lifestyle, to have basic English conversation with robots, and to be interested in English early.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.6
• /
• pp.1089-1094
• /
• 2022

In this paper, a human coexistence-type companion robot that can communicate with people in daily life and alleviate the gap in care personnel was studied. Based on the voice recognition module, servo motor, and Arduino board, a companion robot equipped with a robot arm control function using voice recognition, a position movement function using RC cars, and a voice recognition function was tested and manufactured. As a result of the experiment, the speech recognition experiment according to distance showed the optimal recognition rate at a distance of 5 to 30 cm, and the speech recognition experiment according to gender showed a higher recognition rate in the first tone, monotonous tone. Through the evaluation results of these motion experiments, it was confirmed that a companion robot could be made.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.501-504
• /
• 2002

실시간 제어 시스템은 그 특수성에 의해 개발자에게 상당한 제약이 있었다. 본 논문에서는 실시간 운영체제 중에서 Linux 를 기반으로 한 RTLinux 를 사용하였다. RTLinux를 StrongARM SA-1110 CPU가 탑재된 영상처리 보드에 올리는 과정을 기술하고, RTLinux의 module 이라는 작업 형태를 이용하여 로봇의 카메라에서 획득한 영상을 실시간으로 전송하도록 구현하였다. 또한, 사용자의 입력을 감시하는 부분을 실시간 모듈로 구현하여 제한된 시간 안에 원하는 결과를 산출하도록 구현하였다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.4
• /
• pp.310-319
• /
• 2003

As the importance and the need for network security are increased, many organizations use the various security systems. They enable to construct the consistent integrated security environment by sharing the network vulnerable information among IDS (Intrusion Detection System), firewall and vulnerable scanner. The multiple IDSes coordinate by sharing attacker's information for the effective detection of the intrusion is the effective method for improving the intrusion detection performance. The system which uses BBA (Blackboard Architecture) for the information sharing can be easily expanded by adding new agents and increasing the number of BB (Blackboard) levels. Moreover the subdivided levels of blackboard enhance the sensitivity of the intrusion detection. For the simulation, security models are constructed based on the DEVS (Discrete Event system Specification) formalism. The intrusion detection agent uses the ES (Expert System). The intrusion detection system detects the intrusions using the blackboard and the firewall responses to these detection information.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.951-956
• /
• 2007

This paper suggests a high-speed control method which is suitable for multi-joint robots using a real-time stand-alone controller for general-purpose. The fast processing controller consists of a PCI Interface Board and 2-axe PWM drivers. The PCI Interface Board consists of 32-channel PWM output ports, 32-channel Encoder Counters, 32-channel A/D Converters and 48-channel Digital I/O ports, and all the I/O data transmissions are completed within 1ms. And The 2-axe PWM driver can be redesigned easily in order to embed in each link. Experimental implementations show that the high-speed control method can be used for the real-time control which is essential to controlling of multi-body robots such as humanoid robots. Especially, it is efficient for realizing the model-based motion control in demand of much calculation time by the high I/O communication speed.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.12
• /
• pp.1192-1197
• /
• 2007

This study proposes an automated pegboard utilizing the RFID system with multiple reader antennas for the rehabilitation services and the occupational therapy. The system automates the scoring by detecting the plugging correctness as well as the plugging status. It also aims to increase the patient's interest and the functional intelligence. The system was prototyped and the RFID read rate (over 99.998%) was confirmed. The system was also tested for the automatic capability of the scoring the session. The proposed system will be served as the typical example for the ubiquitous rehabilitation devices.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1066-1069
• /
• 2020

본 논문에서는 임베디드 GPU 보드를 탑재한 로봇에서의 검출 결과를 원격지에서 확인할 수 있는 방법에 대해 기술하였다. 딥러닝 모델의 연산량을 줄이는 방법 대신 Nvidia에서 제공하는 라이브러리를 이용하여 성능을 개선하였고, 로봇의 배터리 소모를 최소화하기 위해 실시간 영상 통신이 아닌 검출이 되었을 시에만 통신이 되게 하여 보다 긴 구동 시간을 얻도록 하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.19-21
• /
• 2020

해가 갈수록 여러 요인들로 인하여 장애인 인구는 증가하고 있다. 하지만 이러한 장애인들을 위한 주변기기의 발전은 미흡한 상황이며 더욱이 장애인들의 여가를 위한 놀이문화, 기술들은 더욱 발전이 더딘 상태이다. 여가 활동은 장애인의 행복에도 직관적인 영향을 끼치는 중요한 부분이다. 따라서 본 논문에서는 장애인들 중 손과 같은 신체를 움직이기 어려운 중증 지체장애인을 위한 오목 플랫폼을 제안한다. 본 논문에서 구현한 오목 플랫폼은 음성인식을 기반으로 사용자가 오목알을 착수하고 싶은 좌표를 음성으로 입력시키면 Dobot 즉 로봇암을 통하여 착수점에 오목알을 착수한다. 실험에선 Google Vocie To Text API를 Python 환경에서 사용하여 사용자의 음성입력을 받았으며 Dobot Studio의 Script에서 입력된 음성 값을 오목판에 1대1로 맵핑시켜 정확한 위치에 착수할 수 있도록 구현하였다. 본 논문의 연구 결과를 응용하면 오목에만 국한되는게 아닌 다양한 보드게임을 구현할 수 있다.