• 제어로봇시스템학회논문지
• /
• 제8권11호
• /
• pp.935-940
• /
• 2002

For robot navigation and visual reconstruction, structure from motion (SFM) is an active issue in computer vision community and its properties arc also becoming well understood. In this paper, when using stereo image sequence and direct method as a tool for SFM, we present a new method for overcoming bas-relief ambiguity. We first show that the direct methods, based on optical flow constraint equation, are also intrinsically exposed to such ambiguity although they introduce robust methods. Therefore, regarding the motion and depth estimation by the robust and direct method as approximated ones. we suggest a method that refines both stereo displacement and motion displacement with sub-pixel accuracy, which is the central process f3r improving its ambiguity. Experiments with real image sequences have been executed and we show that the proposed algorithm has improved the estimation accuracy.

• 제어로봇시스템학회논문지
• /
• 제22권12호
• /
• pp.1034-1039
• /
• 2016

This paper presents the implementation and control of a small-scaled excavator system. The commercial miniature of an excavator system has been modified and its control hardware is embedded to access the feedback control. Encoder sensors are attached to the joint and a force sensor is mounted on the end-effector so that feedback position control is accessible as well as force control. The dynamic model of the excavator system is derived as a four linkage robot arm and its control performances are simulated. Experimental studies of contact force control tasks are conducted to test the control algorithm for the excavator system.

• 대한안전경영과학회지
• /
• 제19권1호
• /
• pp.227-236
• /
• 2017

Smart Manufacturing Factory is a paradigm of the future lead to the fourth industrial revolution that led Germany and the United States. Now the automation of the production facility and won a certain degree, and through the process of integrating the entire process, including planning, design, distribution of information and communication technology products in emerging as a core competitiveness of the national economy. In particular, the company accelerated the smart factory building in order to improve the manufacturing industry, cost savings and productivity simply to incorporate internet of things(IoT),Robot, artificial intelligence, big data technology as a factory automation level of sophistication of the system and out to progress to the level that replaces human labor have. In this we should look at the trend of promoting domestic and foreign factories want to present these smart strategies for Korea.

• 대한산업공학회지
• /
• 제21권2호
• /
• pp.239-254
• /
• 1995

Automated Storage/Retrieval (AS/R) systems have been used mostly in manufacturing or distribution industry in order to store or retrieve palletized items automatically. Since the items ore heavy or bulky, only one pallet at a time is moved by the stacker crane In this study, however, we introduce the "multi -load" AS/R system in which the items to be stored are data storage devices of equal size such as video tape or compact disc. Since the items are small and light multiple items can be stored and retrieved in each trip by using a magazine and a robot arm mounted on the crane Given the magazine capacity, and the locations of retrieval items and empty cells in the rack, the throughput of the multi-load AS/R system will depend on the selection of storage locations and the sequence of visits. We propose four heuristic algorithms for the multi-command. Computer simulation is used to evaluate the four algorithms in terms of throughput and number of back tracking of the crane.

• 한국군사과학기술학회지
• /
• 제17권1호
• /
• pp.33-40
• /
• 2014

Due to its unmanned feature and some of being matured underwater technologies, UUV(Unmanned Undersea Vehicle) is increasingly considered as a utility player in today's battle-field. The operational benefit of submarine-based UUV operation could be enormous yet the integration challenges are significant, particularly for most of small conventionally-powered submarines. In this paper, we consider UUV operational methodology via the conventional submarine's torpedo tube. Two previous attempts having been done to retrieve the UUV through torpedo tube are reviewed, and their pros and cons are also analyzed. Then, an alternative option is proposed for UUV operation via torpedo tube. In addition, some of practical challenges are also discussed in the paper.

• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2014년도 추계학술대회
• /
• pp.231-232
• /
• 2014

립모션 (Leap motion)센서를 사용하여 손동작을 인식하고 손가락의 위치에 따라 미리 지정된 명령어를 보행 로봇에게 전송하여 보행 로봇이 그 명령어를 수행하는 시스템을 개발하였다. 개발언어는 Processing을 사용하고 립모션 센서 라이브러리는 LeapMotionP5를 사용하였다.

• 로봇학회논문지
• /
• 제16권2호
• /
• pp.79-85
• /
• 2021

Soft fluidic actuators (SFAs) are widely utilized in various areas such as wearable systems due to the inherent compliance which allows safe and flexible interaction. However, SFA-driven systems generally require a large pump, multiple valves and tubes, which hinders to develop a miniaturized system with small range of motion. Thus, a highly integrated soft actuator needs to be developed for implementing a compact SFA-driven system. In this study, we propose an electro-hydraulic soft zipping actuator that can be used as a miniature pump. This actuator exerts tactile force as a dielectric liquid contained inside the actuator pressurized its deformable part. In addition, the proposed actuator can estimate the internal dielectric liquid thickness by using its self-sensing function. Besides, the electrical characteristics and driving performance of the proposed system were verified through experiments.

• 한국산업융합학회 논문집
• /
• 제24권4_1호
• /
• pp.397-409
• /
• 2021

This study proposes a new approach to implimentation of robust control and torque control response analysis based on monitoring simulator for smart factory. According to the physical properties of a flexible manipulator, a two time-scale approach, namely, singular perturbation ap proach, is further utilized for thorough analysis and general controller design. It is shown that asymptotic motional tracking can be effectively achieved, whereas the force regulation errors can be made arbitrarily small. For demonstration of the proposed technology performance, experiments of a eight joint flexible manipulator are performed for the proposed control method, and the reliability of proposed control results are illustrated based on monitoring simulator.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권4호
• /
• pp.206-211
• /
• 2022

Recently, the world is facing many difficulties in all areas as a result of price instability and the Russian-Ukraine war. Personally, as many jobs disappear, household income is declining sharply. In particular, the possibility of such bankruptcies is relatively increasing in small and medium-sized enterprises (SMEs), and it is highly likely that this will continue for the time being. In this situation, countries around the world are continuously making efforts to improve corporate productivity. In Korea, the smart factory support project implemented by the Smart Manufacturing Innovation Promotion Team has been continuously promoted for the past several years, providing opportunities for SMEs in need to improve productivity and change the corporate structure. In this study, the current status of smart factory promotion at home and abroad was examined, and problems and improvement measures were studied for the insufficient efficiency in the smart factory promotion system implemented in Korea.