http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
백준민(Junmin Baek),노건우(Gunwoo Noh),서준호(Joonho Seo) 제어로봇시스템학회 2019 제어·로봇·시스템학회 논문지 Vol.25 No.12
Position-tracking devices have been used in various fields, including medical surgery and augmented reality. In this paper, a wireless optical position-tracking module with a processor that can perform self-3D tracking is developed, and the position coordinates of the cube marker are obtained using a position-tracking algorithm. Software is developed to send position coordinate data to the host computer using a wireless UDP network and make it visible at the host computer. To verify the networking system speed and evaluate the accuracy of the position coordinate data, we conducted experiments using the host computer and a two-axis electronic stage. The results demonstrate a speed of 26.81 ㎳ on average with a frequency of 37.3 ㎐. The difference between the moving distance of the actual cube marker and measuring cube marker is 0.764 ㎜ on average, with an RMSE of 0.973 ㎜. This system enables the installation of the device in any space and permits the use of a wireless network, eliminating the data transmission line and simplifying the configuration. Furthermore, many optical position-tracking modules can be installed to solve the problem where the obstacle blocks the cube marker.
카메라 영상과 딥러닝을 이용한 의수로봇 제어 시스템과 파지대상 선정
박해준(Haejune Park),안보현(Bohyeon An),백준민(Junmin Baek),이동규(Dongkyu Lee),김창원(Changwon Kim),주수빈(Subin Joo),권오원(Ohwon Kwon),김민영(Min Young Kim),서준호(Joonho Seo) 제어로봇시스템학회 2020 제어·로봇·시스템학회 논문지 Vol.26 No.5
Robotic prosthetic hands are a device that helps to improve the quality of life for patients without hands. Recently, robotic prosthetic hands can perform various grasping patterns because of improvement of bioengineering and robotics. The research that automatically selects the appropriate operation according to the situation is important. Many previous studies have used EMG signals. However, EMG signals are difficult to generalize because EMG signals vary depending on the position of the muscle. In this study, we developed a system for controlling robotic prosthetic hands using images and deep learning to facilitate generalization. We also proposed a method for selecting a grasping target to be held in the image. These results will help to improve the quality of life of the robotic prosthetic hand user.