http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Yueyuan Zhang (검색결과 4 건)
- 무료
- 기관 내 무료
- 유료
-
PD Control of a Manipulator with Gravity and Inertia Compensation Using an RBF Neural Network
Yueyuan Zhang,김동언,Yudong Zhao,이장명 제어·로봇·시스템학회 2020 International Journal of Control, Automation, and Vol.18 No.12
Dynamic compensation can improve the accuracy of trajectory tracking for industrial manipulators. For irregularly shape or flexible manipulators, however, it is difficult to measure the position of the center of mass (COM) so that its dynamic model cannot be expressed explicitly. This paper proposes a proportional derivative (PD) controller with radial basis function neural network based gravity and inertia compensation (RBFNN-GIC). The RBFNN is utilized to estimate the gravity disturbance and to enable identification of COM to calculate thecompensated inertia term. The proposed strategy based on the dynamic model can be used on any robot arm whose COM, gravity and inertia are difficult to obtain. To demonstrate the optimization and effectiveness of proposed PD controller, comparative experiments between the proposed control scheme and the traditional data-fitting method least mean square method (LMS) are conducted on a 3 degree of freedom (DOF) robotic manipulator.
-
Yudong Zhao,Yueyuan Zhang,이장명 제어·로봇·시스템학회 2019 International Journal of Control, Automation, and Vol.17 No.5
In this paper, a new two-layer control strategy which combines Kinematic Controller based on LyapunovTheory (KCLT) with Dynamic Controller based on Sliding Mode (DCSM) is proposed to solve the problem ofleader-follower formation control for multiple wheeled mobile robots (M-WMR). An augmented distance-angleleader-follower formation kinematic is constructed to describe the formation states, and a 2D LiDAR sensor is utilizedto measure the states instead of using camera and image processing on each follower. Instead of transferringthe measured formation states into reference position command for each follower, KCLT is designed to generatefollower’s velocity command. By taking the velocity command of followers as reference signals, DCSM is implementedto realize formation control. Lyapunov stability theory verifies that with the designed controller all the errorsignals can converge to 0 theoretically, which implies formation control of M-WMR under the proposed methodcan be realized. Real experiments with one leader and two followers are carried out to demonstrate the effectivenessof the proposed control schema. In order to verify the robustness of the proposed method, the reference rotationalvelocity of the leader robot is designed to change between +0:2 rad/s and 0:2 rad/s at some specified position. And the experimental results are compared with that of traditional proportional-integral-derivative (PID) method.
-
CAO, Yiming,Shu Zhang,Man Ching Esther Chan,Yueyuan Kang 서울대학교 교육연구소 2021 Asia Pacific Education Review Vol.22 No.2
This study investigated how teachers in China perceived the effects of online instruction on mathematics learning and examined the challenges they encountered when the country shifted to online instruction during the COVID-19 pandemic. We interviewed 152 mathematics teachers from 20 cities (municipalities) or provinces in China and adopted the four-component didactic tetrahedron model (teacher, technology, student, and mathematics) to identify their struggles with technology, teacher–student interactions, and delivery of mathematics instruction. Results showed that the teachers believed that the effectiveness of online teaching largely depends on student self-discipline. Analysis suggested a need to expand technology use during instruction, reshape the way teachers interact with students, and reorganize teaching methods in face-to-face classroom instruction. This research provided insights into integrating technology with instructional practice, the critical role of teachers in online learning, and other factors that may determine the effectiveness of online teaching.
-
Qualitative Analysis of Single Object and Multi Object Tracking Models
Sumaira Manzoor,Kyu-Hyun Sung,Yueyuan Zhang,Ye-Chan An,Tae-Yong Kuc 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
Tracking the object(s) of interest in the real world is one of the most salient research areas that has gained widespread attention due to its applications. Although different approaches based on traditional machine learning and modern deep learning have been proposed to tackle the single and multi-object tracking problems, these tasks are still challenging to perform. In our work, we conduct a comparative analysis of eleven object trackers to determine the most robust single object tracker (SOT) and multi-object tracker (MOT). The main contributions of our work are (1) employing nine pre-trained tracking algorithms to carry out the analysis for SOT that include: SiamMask, GOTURN, BOOSTING, MIL, KCF, TLD, MedianFlow, MOSSE, CSRT; (2) investigating MOT by integrating object detection models with object trackers using YOLOv4 combined with DeepSort, and CenterNet coupled with SORT; (3) creating our own testing videos dataset to perform experiments; (4) performing the qualitative analysis based on the visual representation of results by considering nine significant factors that are appearance and illumination variations, speed, accuracy, scale, partial and full-occlusion, report failure, and fast motion. Experimental results demonstrate that SiamMask tracker overcomes most of the environmental challenges for SOT while YOLOv+DeepSort tracker obtains good performance for MOT. However, these trackers are not robust enough to handle full occlusion in real-world scenarios and there is always a trade-off between tracking accuracy and speed.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
