Prof. Sam Shuzhi Ge
National University of Singapore, Singapore (IEEE FELLOW)
“Cooperative Dynamic Planning and Control in Complex
Abstract: Multi-agent systems are in great demand for the modern society driven by the need for unmanned vehicles on land, in air and under water, which require more works to study the existing technical difficulties. In this lecture, I will first give a brief introduction on the dynamic cooperative planning which helps to improve the search speed to achieve real-time planning and control, then go through works of multi-agent control driving agents to track moving dynamic targets or form a specific formation configuration in constrained space, the two-layer formation, the fast hedging and control techniques in complex airspace. I would like to conclude my lecture by presenting an experiment using heterogeneous aircraft to verify the autonomous avoidance and avoidance of multi-heterogeneous vehicles in low-altitude airspace.
Biodata: Prof. Shuzhi Sam Ge, IEEE Fellow, P.Eng, is the Director of Social Robotics Lab, Interactive Digital Media Institute, and Supervisor of Edutainment Robotics Lab, Department of Electrical and Computer Engineering, The National University of Singapore. He received his PhD degree and DIC from the Imperial College, London, and BSc degree from Beijing University of Aeronautics & Astronautics. He has (co)-authored three books, and over 300 international journal and conference papers. He serves as Vice President of Technical Activities, 2009-2010, and Member of Board of Governors, 2007-2009, and Chair of Technical Committee on Intelligent Control, 2005-2008, of IEEE Control Systems Society. He served as General Chair and Program Chair for a number of IEEE international conferences. He is the Editor-in-Chief, International Journal of Social Robotics, and Springer. He has served/been serving as an Associate Editor for a number of flagship journals including IEEE Transactions on Automatic Control, IEEE Transactions on Control Systems Technology, IEEE Transactions on Neural Networks, and Automatica, and Book Editor for Taylor & Francis Automation and Control Engineering Series. He was the recipient of Changjiang Guest Professor, MOE, China, 2008; and Fellow of IEEE, USA, 2006.
Prof. Chun-Yi Su
Concordia University, Canada
“Modeling and Control of Dielectric Elastomer Actuators in Soft Robots”
Abstract: Over the last decade, soft robots have received tremendous interests for their potential applications. Soft robots mostly refer to robotic systems with soft or compliant structures and muscle-like actuation using soft or highly deformable materials. Unlike conventional robots, they can show high deformation under actuation and change their shapes continuously along their body length, similar to octopus arms, earthworms, and elephant trunks. The key challenge for creating soft robots that achieve their full potential is the development of controllable soft bodies using materials that integrate sensors, actuators, and computation, that together enable the body to deliver the desired behavior. Among soft actuation materials, dielectric elastomers (DEs) represent an emerging/innovative class of soft actuation materials which exhibit relatively large deformations when solicited by an electric field.
On the other hand, DEs are viscoelastic materials meaning that their stiffness changes with strain rate and frequency. Viscoelasticity complicates the modeling and control of the material response which is often characterized by creep, hysteresis, and stress relaxation phenomena. Owing to these intrinsic nonlinear and time variant characteristics, the precise control of DEs to determine the amount of voltage needed to obtain the deformation for soft robots becomes a non-trivial problem. In this talk, two relevant research topics are introduced in detail: modeling and control. First, the crucial techniques are presented for the model development. Next, nonlinear control based the developed model will be discussed. Finally, the future trends of the related research fields are given.
Biodata: Prof. Chun-Yi Su received his Ph.D. degrees in control engineering from South China University of Technology in 1990. After a seven-year stint at the University of Victoria, he joined Concordia University in 1998, where he is currently a Professor of Mechanical, Industrial & Aerospace Engineering and holds the Concordia University Research Chair in Control. He has also held several short-time visiting positions including a Chang Jiang Chair Professorship by China’s Ministry of Education and JSPS Invitation Fellowship from Japan.
Dr. Su’s research covers control theory and its applications to various mechanical systems, with a recent focus on control of systems involvinghysteresis nonlinearities. He has made fundamental contribution to modeling and control of nonlinear systems involving hysteresis nonlinearities. He developed some fundamental properties for the early development of constrained robotic control. He is the author or co-author of over 400 publications, which have appeared in journals, as book chapters and in conference proceedings.
Prof. Xudong Jiang,
Nanyang Technological University, Singapore
“Sematic Image Segmentation by Deep Machine Learning”
Abstract: Scene image segmentation is a challenging task as it need classify every pixel in the image. It is crucial to exploit discriminative context and aggregate multi-scale features to achieve better segmentation. Context is essential for semantic segmentation. Due to the diverse shapes of objects and their complex layout in various scene images, the spatial scales and shapes of contexts for different objects have very large variation. It is thus ineffective or inefficient to aggregate various context information from a predefined fixed region. In this talk, I will first present a novel context contrasted local feature that not only leverages the informative context but also spotlights the local information in contrast to the context. The proposed context contrasted local feature greatly improves the parsing performance, especially for inconspicuous objects and background stuff. Furthermore, I will present a scheme of gated sum to selectively aggregate multi-scale features for each spatial position. The gates in this scheme control the information flow of different scale features. Their values are generated from the testing image by the proposed network learnt from the training data so that they are adaptive not only to the training data, but also to the specific testing image. Finally, I will present a scale- and shape-variant semantic mask for each pixel to confine its contextual region. To this end, a novel paired convolution is proposed to infer the semantic correlation of the pair and based on that to generate a shape mask. Using the inferred spatial scope of the contextual region, a shape-variant convolution is controlled by the shape mask that varies with the appearance of input. In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region. In addition, this work also proposes a labeling denoising model to reduce wrong predictions caused by the noisy low-level features. This talk is based on two papers: H. Ding, X. Jiang, et al, “Context contrasted feature and gated multi-scale aggregation for scene segmentation,” CVPR’2018 Oral, and H. Ding, X. Jiang, et al, “Semantic Correlation Promoted Shape-Variant Context for Segmentation,” CVPR’2019 Oral.
Biodata: Prof. Xudong Jiang is currently in the School of Electrical and Electronic Engineering as Professor and Director of the Centre for Information Security. He received his Bachelor and Master degrees from the University of Electronic Science and Technology of China, in 1983 and 1986, and the Ph.D. degree from the University of German Federal Armed Forces, Hamburg, Germany, in 1997, all in electrical and electronic engineering. From 1986 to 1993, he was a Lecturer at the University of Electronic Science and Technology of China where he received two Science and Technology Awards from the Ministry of Electronic Industry of China. From 1993 to 1997, he was with the University of German Federal Armed Forces Hamburg, Germany, as a scientific assistant. From 1998 to 2002, he was with Nanyang Technological University, Singapore, as a Senior/Research Fellow where he developed a fingerprint verification algorithm that achieved the fastest speed with the second most accuracy in the International Fingerprint Verification Competition (FVC2000). From 2002 to 2004, he was a Lead Scientist and Head of the Biometrics Laboratory at the Institute for Infocomm Research, A*STAR, Singapore. Dr Jiang has published over 100 international conference and journal papers. He is also an inventor of 7 patents (3 of them are United States patents). Dr Jiang is a senior member of IEEE and has been serving as Editorial Board Member, Guest Editor and Reviewer of multiple international journals, and serving as Program Committee member, Keynote Speaker and Session Chair of multiple international conferences.
Dr. Yi Zhou
Singapore Institute of Technology, Singapore
“Applied Research in Transportation: Safer, Better and more Cost Effective”
Abstract: This talk will share applied research in transportation especially on railway and road mobility.
Telematics, informative transportation and autonomous vehicles are disruptive technologies that changing the landscape of transportation and mobility.
Condition monitoring and predictive maintenance are the trends for effective maintenance in public transport.
The speaker will share his observations and thoughts on these technologies.
Biodata: Dr ZHOU Yi is an Assistant Professor at Singapore Institute of Technology (SIT). He was a lecturer at Singapore University of Technology and Design and Singapore Polytechnic before joining SIT. Dr ZHOU has been a council member of Institution of Engineers, Singapore (IES) since 2012 and currently serves as chairman of Electrical, Electronic and Computing Engineers Technical Committee and deputy chairman of Railway and Transportation Technical Committee. Dr Zhou was a co-chairman for Singapore LTA Engineering Challenge in 2016. Dr ZHOU has also been secretary of RoboCup (Singapore) Association and National Committee since 2009. He chaired RoboCup 2010 Rescue Simulation League.