In this talk, we aim to present a fully autonomous and fully functional infrastructure inspection and information management system with advanced AI and unmanned aerial systems (UAS) technologies. The system includes sophisticated unmanned aerial hardware platform and software systems for automatic flight control and task and motion planning, artificial intelligent algorithms and software platform for image and infrared data processing, i.e., crack, spalling, delamination and other defect detections, and building information modeling (BIM) and management system integrated with detailed geographical information systems (GIS). Compared with the manual inspection, the system that we have developed has the advantages of being more economical, safer, flexible and efficient. It can also be adopted for other industrial applications.
Ben M. Chen received his B.Sc. degree in mathematics and computer science from Xiamen University, China, in 1983, M.Sc. in electrical engineering from Gonzaga University, USA, in 1988, and Ph.D. in electrical and computer engineering from Washington State University, USA, in 1991. He is currently a Professor of Mechanical and Automation Engineering at the Chinese University of Hong Kong (CUHK). He was a Provost's Chair Professor in the Department of Electrical and Computer Engineering at the National University of Singapore, before joining CUHK in 2018. He was an Assistant Professor in the Department of Electrical Engineering at the State University of New York at Stony Brook, USA, in 1992–1993. His current research interests are in unmanned systems and their applications.
Prof. Chen is a Fellow of IEEE and Fellow of Academy of Engineering, Singapore. He has authored/co- authored hundreds of journal and conference articles, and a dozen research monographs in control theory and applications, unmanned systems and financial market modeling. He had served on the editorial boards of a dozen international journals including Automatica and IEEE Transactions on Automatic Control. He currently serves as an Editor-in-Chief of Unmanned Systems. Prof. Chen has received a number of research awards. His research team has actively participated in international UAV competitions and won many championships in the contests.
Details can be found at http://www.mae.cuhk.edu.hk/~bmchen/main.html
Convolutional neural networks (CNNs) have made great breakthroughs in 2D computer vision. However, their irregular structure makes it hard to harness the potential of CNNs directly on meshes. A subdivision surface provides a hierarchical multi-resolution structure, in which each face in a closed 2-manifold triangle mesh is exactly adjacent to three faces. Motivated by these two observations, this paper presents SubdivNet, an innovative and versatile CNN framework for 3D triangle meshes with Loop subdivision sequence connectivity. Making an analogy between mesh faces and pixels in a 2D image allows us to present a mesh convolution operator to aggregate local features from nearby faces. By exploiting face neighborhoods, this convolution can support standard 2D convolutional network concepts, e.g. variable kernel size, stride, and dilation. Based on the multi-resolution hierarchy, we make use of pooling layers which uniformly merge four faces into one and an upsampling method which splits one face into four. Thereby, many popular 2D CNN architectures can be easily adapted to process 3D meshes. Meshes with arbitrary connectivity can be remeshed to have Loop subdivision sequence connectivity via self-parameterization, making SubdivNet a general approach. Extensive evaluation and various applications demonstrate SubdivNet's effectiveness and efficiency.
Prof. Shi-Min Hu is currently a professor in the department of Computer Science and Technology, Tsinghua University, Beijing. He received the PhD degree from Zhejiang University in 1996. His research interests include Computer Graphics, intelligent processing of visual media, Deep learning framework and system software. He has published more than 100 papers in journals and refereed conference. He is Editorin-Chief of Computational Visual media, and on editorial board of several journals, including Computer Aided Design, Computer & Graphics. He is Chair of Asiagraphics, and vice president of China Computer Federation.
Details can be found at http://cg.cs.tsinghua.edu.cn/shimin.htm
For mechatronic systems, nonlinearities (frictions, backlash, saturation, etc.), complex internal dynamics, time-varying parameters, noise, external disturbances and complex work tasks make control design a very challenging work. In this talk we will discuss on various advanced modeling, analysis and intelligent control techniques for mechatronic control systems. There are also development requirements for intelligent functions of mechatronic systems, such as parameter self-adjustment and adaptation, sensor less control, vibration suppression, etc. Some new research developments and results on this topic will be introduced. Considering the characteristics of mechatronic control system, several kinds of composite control design schemes based on disturbance estimation and compensation are presented with experimental or application verification results.
Shihua Li was born in Pingxiang, China, in 1975. He earned his B.Eng., M.Sc. and Ph.D. degrees in control science and engineering from Southeast University, Nanjing, China in 1995, 1998 and 2001, respectively. Since 2001, he has been with the School of Automation, Southeast University, where he is currently a chair Professor and the Director of the Mechatronic Systems Control Laboratory. He visited UC Berkeley from 2006.9-2007.9, RMIT University 2011.3-2011.6, University of Minnesota at Twin Cities 2012.4-2012.10, University of Hong Kong 2014.6-2014.8 and University of Western Sydney 2017.7-2017.8.
He is a fellow of IEEE and IET, the Chairman of the IEEE Industrial Electronics Society (IES) Nanjing Chapter. He serves as members of the Technical Committees on System Identification and Adaptive Control, Nonlinear Systems and Control and Variable Structure and Sliding Mode Control of the IEEE CSS and members of the Technical Committees on Electrical Machines, and Motion Control of the IEEE Industrial Electronics Society. He is a member of the Technical Committee on Control Theory of Chinese Association of Automation. He serves as associate editors of IEEE Transactions on Industrial Electronics, International Journal of Robust and Nonlinear Control, Advanced Control for Applications, etc.
His main research interests lie in modeling, analysis, and nonlinear control theory (nonsmooth control, disturbance rejection control, adaptive control, etc.) with applications to mechatronic systems, intelligent transportation systems and others. He has published over 200 journal papers and two books. He is one of the Clarivate Analytics (originally Thomson Reuters) Highly Cited Researchers (Engineering) all over the world from 2017 to 2020, one of the Most Cited Chinese Researchers from Elsevier (Control and system engineering), from 2015 to 2020. He is a winner of best paper in the IET Control Theory & Applications 2017, a winner of annual ICI prize for best paper in the Transactions of the Institute of Measurement 2016 and a winner of outstanding paper in 2019 SAMCON conference. He is a winner of the 6th Nagamori Award from Nagamori Foundation in 2020.
Details can be found at https://automation.seu.edu.cn/lsh/list.htm