• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.8
• /
• pp.471-481
• /
• 2003

The acts of biological immune system are similar to the navigation for autonomous mobile robots under dynamically changing environments. In recent years, many researchers have studied navigation algorithms using artificial immune networks. Conventional artificial immune algorithms consist of an obstacle-avoidance behavior and a goal-reaching behavior. To select a proper action, the navigation algorithm should combine the obstacle-avoidance behavior with the goal-reaching behavior. In this paper, the neural network is employed to combine the behaviors. The neural network is trained with the surrounding information. the outputs of the neural network are proper combinational weights of the behaviors in real-time. Also, a velocity control algorithm is constructed with the artificial immune network. Through a simulation study and experimental results for a autonomous mobile robot, we have shown the validity of the proposed navigation algorithm.

• Electronics and Telecommunications Trends
• /
• v.37 no.1
• /
• pp.1-9
• /
• 2022

With the development of artificial intelligence, many studies have focused on evaluating abnormal situations by using various sensors, as industries try to automate some of the surveillance and security tasks traditionally performed by humans. In particular, mobile robots using multimodal sensors are being used for pilot operations aimed at helping security robots cope with various outdoor situations. Multiagent systems, which combine fixed and mobile systems, can provide more efficient coverage (than that provided by other systems), but network bottlenecks resulting from increased data processing and communication are encountered. In this report, we will examine recent trends in object recognition and abnormal-situation determination in various changing outdoor security robot environments, and describe an outdoor security robot platform that operates as a multiagent equipped with a multimodal sensor.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.6
• /
• pp.22-29
• /
• 2022

In this study, an automatic marking system for fabric inspection machines was developed. The main objectives of the study were to promote intelligence and automation for the inspection process, as well as to increase textile industrial productivity. Generally, when a worker manually inspects and marks a fabric, human error and reduced efficiency are unavoidable. To overcome these problems, we developed an automatic marking system that uses robots. This system incorporates a vision camera to automatically recognize defects, and an optical fiber sensor to detect the side of the fabric. To verify the performance, the control system sends a command directly to the robot to mark the fabric. Finally, the actual production confirmed that the proposed system could perform the desired motion.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.352-357
• /
• 2023

Since robotic assembly in an unstructured environment is very difficult with existing control methods, studies using artificial intelligence such as reinforcement learning have been conducted. However, since long-time operation of a robot for learning in the real environment adversely affects the robot, so a method to shorten the learning time is needed. To this end, a method based on a pre-trained neural network was proposed in this study. This method showed a learning speed about 3 times than the existing methods, and the stability of reward during learning was also increased. Furthermore, it can generate a more optimal policy than not using a pre-trained neural network. Using the proposed reinforcement learning-based assembly trajectory generator, 100 attempts were made to assemble the power connector within a random error of 4.53 mm in width and 3.13 mm in length, resulting in 100 successes.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.652-655
• /
• 2020

최근 딥 러닝을 이용해 기계로 인간을 대체하는 스마트 팩토리에 대한 연구 및 개발이 활발히 진행되고 있다. 그러나 FPCB를 Placing하는 방법에 기계를 도입하는 과정은 발전이 더딘 상태이다. 현재 로봇 팔을 이용해 Placing하는 방법은 사람이 직접 로봇 팔을 튜닝해 사용하고 있다. 이에 본 논문은 딥 러닝을 이용한 영상처리 기법을 활용해 FPCB를 사람의 개입 없이 트레이에 삽입하는 기법을 개발하였다. 이를 위해 여러 알고리즘을 비교한 후 각각의 장단점을 고려해 적합한 알고리즘을 제시하였다. 본 논문에서 제시하는 기법은 FPCB에 아무 행동을 가하지 않으며, 힘 센서, 깊이 센서 등 기타 센서들의 도움 없이 RGB 센서(카메라)를 통해 획득한 이미지만을 이용해 자동화가 가능하다. 또한, 개발 단계에서 실제 기계를 이용해 이미지 촬영, 이동 등을 진행했기 때문에 조명, 로봇 팔 위치 등 알고리즘 외 조건들에 영향을 받지 않고 실제 사용이 가능하다.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.243-262
• /
• 2022

In this study, eye tracking was used for the appearance of the robot during the social robot design study. During the research, each part of the social robot was designated as AOI (Areas of Interests), and the user's attitude was measured through a design evaluation questionnaire to construct a design research model of the social robot. The data used in this study are Fixation, First Visit, Total Viewed, and Revisits as eye tracking indicators, and AOI (Areas of Interests) was designed with the face, eyes, lips, and body of the social robot. And as design evaluation questionnaire questions, consumer beliefs such as Face-highlighted, Human-like, and Expressive of social robots were collected and as a dependent variable was attitude toward robots. Through this, we tried to discover the mechanism that specifically forms the user's attitude toward the robot, and to discover specific insights that can be referenced when designing the robot.

• Journal of Practical Engineering Education
• /
• v.12 no.2
• /
• pp.339-351
• /
• 2020

In response to changes in Fourth Industrial Revolution in recent years, the field of education has focused on development of the human resources in the areas of artificial intelligence (AI: Artificial Intelligence) and industrial robot. Due to particular interest in these areas, the importance of developing integrated human resources equipped with artificial intelligence technology is emphasized in higher education and vocational competence development. In regards to rapid changing environment, this study created a program "Fostering personalized AI integrated human resource" and established an operational model correspond to latest personalized education trend. The established operational model was conducted twice using Delphi survey with experts in AI and innovative education in order to verify the suitability of program's basic structure, training process, and the sub-components of the operational strategy. The final training model was applied to the online vocational training platform (STEP) and a plan was proposed to establish a personalized training model to foster an AI integrated competent individual.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.877-883
• /
• 2021

Artificial intelligence technology is widely used in industrial and smart home fields such as manufacturing robots, artificial intelligence speakers, and robot vacuum cleaners. In this paper, we designed and implemented a 1:1 chatbot system based on artificial intelligence for use in RCMS (Real-time Cash Management System). The RCMS chatbot implemented in this paper was constructed with a total of 210 query scenarios in nine areas, including research expenses and system usage, based on 13,500 questions and answers from existing online bulletin boards. The chatbot is expected to solve the problem of insufficient number of counselors and to increase user satisfaction by responding to the researcher's inquiries after working hours, and the recommendation service for the cost of use, which had the most inquiries from researchers, reduces the number of consultations. It is expected to improve the quality of answers to other counseling inquiries.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.405-421
• /
• 2023

Strong wind is the main factors of wind-damage of high-rise buildings, which often creates largely economical losses and casualties. Wind pressure plays a critical role in wind effects on buildings. To obtain the high-resolution wind pressure field, it often requires massive pressure taps. In this study, two traditional methods, including bilinear and bicubic interpolation, and two deep learning techniques including Residual Networks (ResNet) and Generative Adversarial Networks (GANs), are employed to reconstruct wind pressure filed from limited pressure taps on the surface of an ideal building from TPU database. It was found that the GANs model exhibits the best performance in reconstructing the wind pressure field. Meanwhile, it was confirmed that k-means clustering based retained pressure taps as model input can significantly improve the reconstruction ability of GANs model. Finally, the generalization ability of k-means clustering based GANs model in reconstructing wind pressure field is verified by an actual engineering structure. Importantly, the k-means clustering based GANs model can achieve satisfactory reconstruction in wind pressure field under the inputs processing by k-means clustering, even the 20% of pressure taps. Therefore, it is expected to save a huge number of pressure taps under the field reconstruction and achieve timely and accurately reconstruction of wind pressure field under k-means clustering based GANs model.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1109-1114
• /
• 2003

In this paper, task control architecture is proposed for a mobile robot with behaviors based on cognition theory to endow the robot intelligence. In the task control architecture, task manager is introduced especially for the management of computational resource. The management is based on classical RMS (Rate Monotonic Strategy), but with online rate modulation strategy. The rate modulation is performed using the value variances of behavior execution for the task. Because the values are based on natively uncertain sensor information, they are modeled using PDF (probability Density Function). As a rate modulation process, the range of the rate modulation is defined firstly by real-time constraints of RMS and discrete control stability of behaviors. With the allowable range, rate modulations are performed considering harmonic bases to maintain utilization bound without decrease. To evaluate the efficiency of the proposed rate modulation strategy, a simulation test is performed to compare the efficiency between the control architecture with the proposed strategy and previous one. A performance index with the formalization of propensity of resource allocation is proposed and utilized for the simulation test. To evaluate the appropriateness of the performance index, the performance index is compared with practical one through a practical simulation test.