Research Hotspot Symposium Series of the IET Cyber-Systems and Robotics
No. 1 Fluids, Robotics & Applied Math X Workshop, Hangzhou, China
- November 3, 2018
We are going to launch a multidisciplinary workshop on the challenging issues at the cross-area of fluid mechanics, bio-inspired robotics and their related applied mathematics.
Speakers and presentation titles (in an alphabetic order of the initial letters of last names):
- Shengze Cai :: 蔡声泽 (College of Control Science and Engineering, Zhejiang University), Flow visualization and measurement via computer vision technologies
- Pakpong Chirarattananon (Department of Mechanical and Biomedical Engineering, City University of Hong Kong), Biologically Inspired Robots: Flying Like a Fly, Swimming Like a …. Fly?
- Qi Gao :: 高琪 (School of AA, Zhejiang University), 基于流动控制方程作为物理约束的三维实验数据后处理技术
- Tiefeng Li :: 李铁风 (School of AA, Zhejiang University), Soft Robot made of hydrogel and electroactive polymer
- Zhi Lin :: 林智 (School of Mathematics, Zhejiang University), Stochastic Hydrodynamic Model for Biogenic Mixing
- Lianqing Liu :: 刘连庆 (Professor Shenyang Institute of Automation, Chinese Academy of Science, China), Living Cell based Modular Micro Robot Fabricated by Robotic Micro-Manipulation System
- Jia Pan :: 潘佳 (Department of Mechanical Engineering and Biomedical Engineering, City University of Hong Kong), Learning-based Robotic Controller Design and Optimization
- Jianghao Wu :: 吴江浩 (School of Transportation Science and Engineering, Behang University), 仿生微型飞行器设计中的空气动力学机理及其应用
|9:10 -9:50||报告题目：Stochastic Hydrodynamic Model for Biogenic Mixing
报告人：林智(School of Mathematics, Zhejiang University)
|9:50-10:30||报告题目：Living Cell based Modular Micro Robot Fabricated by Robotic Micro-Manipulation System
报告人：刘连庆 (Professor Shenyang Institute of Automation, Chinese Academy of Science, China)
|10:30-11:10||报告题目：Biologically Inspired Robots: Flying Like a Fly, Swimming Like a …. Fly?
报告人：Pakpong Chirarattananon (Department of Mechanical and Biomedical Engineering, City University of Hong Kong)
报告人：吴江浩 (School of Transportation Science and Engineering, Behang University)
|13:30-14:10||报告题目：Soft Robot made of hydrogel and electroactive polymer
报告人： 李铁风 (School of AA, Zhejiang University)
|14:10-14:50||报告题目：Learning-based Robotic Controller Design and Optimization
报告人：潘佳(Department of Mechanical Engineering and Biomedical Engineering, City University of Hong Kong)
报告人：高琪(School of AA, Zhejiang University)
|15:30-16:10||报告题目：Flow visualization and measurement via computer vision technologies
报告人：蔡声泽 (College of Control Science and Engineering, Zhejiang University)
Schedule and abstract information:
- Soft Robot made of hydrogel and electroactive polymer, by Tiefeng Li（李铁风）
Abstract: The softness and large strain actuation of responsive hydrogels promise the potential to fabricate soft devices, which can function as a robotic system. The key challenges lie in the fabrication of soft devices with robust actuating ability and biocompatibility to the attached organ. Here we present a solution that integrates the responsive hydrogel membrane, electro-active polymer and flexible electronics can be integrated into a electromechanical device. As an example, the actuation assisting function of this soft device for shrinking an animal bladder is presented. The mechanical behaviors of the balloon-like soft device are experimentally and theoretically investigated. The concepts are applicable to other applications such as soft implants, soft robotics, and microfluidics.
- Biologically Inspired Robots: Flying Like a Fly, Swimming Like a …. Fly?, by Pakpong Chirarattananon, Assistant Professor, Department of Biomedical Engineering City University of Hong Kong (Email: email@example.com; Web: http://ris.mbe.cityu.edu.hk)
Abstract: Using only tiny nervous system, flying insects are able to perform superlative aerodynamic feats such as deftly avoiding a striking hand or landing on flowers buffeted by wind. These amazing creatures inspire scientists and engineers to understand and translate this ubiquitous form of locomotion into man-made machines. In this talk, I will discuss challenges that arise in the fabrication and control and exciting research outcomes related to millimeter-scale biologically-inspired flapping-wing robots. Challenges for the development of such small robots are associated to actuation, power and complex fluid-structure interactions. Through multiple iterations of designs, experiments and theoretical modeling, over the years, not only did we demonstrate a stable tethered flight of an insect-scale robot, but complex maneuvers have also been realized. The flapping-wing robot is capable of flying, landing on a wall, or swimming and transitioning out of the water.
Biography: Pakpong Chirarattananon received his Bachelor and Master degrees from University of Cambridge, UK, and a Ph.D. degree from Harvard University under the supervision of Professor Robert Wood in 2014. His graduate work was centred on the dynamics and control for insect-scale flapping-wing robots. In December 2014, he joined the Department of Mechanical and Biomedical Engineering as an Assistant Professor and founded the Robotic and Intelligent Systems Laboratory at City University of Hong Kong. Dr Chirarattananon is broadly interested in applying control and dynamic system theories to study aerial and biologically-inspired robotic systems. He has published in Science, Science Robotics, and has been nominated as the best student paper award finalist at the 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) and the best paper award finalist at the 2014 IEEE International Conference on Biomedical Robotics and Biomechatronics. Dr Chirarattananon is serving as the publication co-chair for the upcoming 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) and the 2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM).
- Stochastic Hydrodynamic Model for Biogenic Mixing, by Zhi Lin 林智
Abstract: Biogenic mixing (the mixing and transport due to the swimming of marine species) has attracted a significant amount of interdisciplinary research efforts in recent years. In previous work, the applicant has contributed in deriving a stochastic hydrodynamic model that incorporates both deterministic fluid dynamics models and statistic description for stochastic swimming with a bottom-up approach and leads to a formula for the effective diffusivity. This model provides a new approach for the study of biogenic mixing and similar phenomena in other areas of science and engineering. Recently, we are seeking to improve the model and its simulation by considering various complicated factors, such as anisotropic swimming, nonlinear coupling by massive schooling.
- Ph.D.(2007), Mathematics, University of North Carolina, Chapel Hill, North Carolina, USA :: Thesis: “Scalar Intermittency in Random Flows: Modelling and Simulation” • Advisors: Professor Richard McLaughlin and Professor Roberto Camassa
- B.Sc.(2002), Applied Mathematics and Applied Software, South China University of Technology, China
- 2018/01 ~ Present, Professor, School of Mathematical Sciences, Zhejiang University, Hangzhou, China
- 2011/08 ~ 2017/12, Special-Termed Professor, Department of Mathematics, Zhejiang University, Hangzhou, China
- 2009/09 ~ 2011/08, Postdoctoral Fellow, Institute for Mathematics and its Applications, Minneapolis, Minnesota, USA
- 2007/09 ~ 2009/05, Postdoctoral Assistant Professor, Department of Mathematics, University of Michigan, Ann Arbor, Michigan, USA
- 基于流动控制方程作为物理约束的三维实验数据后处理技术, by Qi Gao 高琪
- Living Cell based Modular Micro Robot Fabricated by Robotic Micro-Manipulation System, by Lianqing Liu 刘连庆 (Professor Shenyang Institute of Automation, Chinese Academy of Science, China)
Abstract: Micro-robots have a great application prospect in the biomedical field due to the feature of small size. To solve the issues of energy supply and bio-compatibility of micro-robots, the bio-syncretic micro-robots actuated by living cells have been studied widely. However, the fabrication, assembling and control of the bio-syncretic micro-robots are the main challenges for the development of the bio-syncretic micro-robots. In this talk, manufacture and control of the living cells based modular micro robots will be discussed. Firstly, a robotic micro-manipulation system will be introduced to implement the high-throughput fabrication of the biological modules of micro robots, and to execute the on-line flexible assembling of the bio-syncretic robots by the fabricated living cells based modules. Then, an approach based on circularly distributed multiple electrodes (CE) will be induced to improve the differentiation of myoblast cells and characterize the electro-responsive beating behavior of living myotubes for the development of bio-syncretic micro robots. Moreover, a biomimetic bio-syncretic crawler actuated by living myotubes was demonstrated to move under the control of the CE. This talk will not only be related to the micro-robots, but will be also informative for biological tissue engineering and drugs screening.
- Learning-based Robotic Controller Design and Optimization, by Jia Pan 潘佳
Abstract: Artificial intelligence has recently been used to design and optimize robotic controllers in a data-driven manner. This talk will introduce our recent work on how to use machine learning techniques to compute high-quality feedback controllers for several typical applications: the cloth assembly, the multi-robot warehouse scheduling, and the robot navigation in dense crowds.
Biography: Jia Pan received his Ph.D. degree in Computer Science from the University of North Carolina at Chapel Hill in 2013. He has been with the City University of Hong Kong since 2015. His research interests include robotics and artificial intelligence.
- 仿生微型飞行器设计中的空气动力学机理及其应用, by Jianghao Wu 吴江浩
- Flow visualization and measurement via computer vision technologies, by Shengze Cai 蔡声泽
Abstract: Particle image velocimetry (PIV), as a flow visualization technology, can provide non-intrusive quantitative measurement of the velocity fields. This technique has been studied intensively and plays an increasingly important role in experimental fluid mechanics. To go deeper insight into complex flow phenomena, precise motion estimation methods dedicated to fluid mechanics and towards real-time measurement are being investigated in this talk. On the one hand, variational optical flow computation coupled with the stochastic transport theory is proposed for turbulent flow estimation. This formulation can extract accurate velocity fields from particle images as well as scalar images. On the other hand, deep learning technique is also introduced to PIV estimation with high efficiency, which is promising for real-time measurement and active flow control.
Title: Security in Cyber-Physical Systems: A Control Systems Perspective
演讲人：Prof. Petros Voulgaris, UIUC, Fellow of IEEE
Cyber-physical systems (CPS) have become ubiquitous in engineering and have extended the range of aerospace applications to several new domains. Unmanned Arial Vehicles (UAV) are typical examples of CPS that can execute cooperative missions of increasing complexity without constant supervision of human operators e.g., military reconnaissance and strike operations, border patrol missions, forest fire detection, police surveillance, and recovery operations to name a few. Similarly, current and future space applications such as satellite swarms and distributed spacecraft systems, autonomous and aerospace robotic systems, depend critically on the synergy of cyberspace with the physical components.
Pertinent to CPS is the notion of security, which is of paramount importance in aerospace, power, transportation, manufacturing, etc. The concept of security to malicious attacks brings an important new dimension in the design CPS. In this talk, we present some aspects of this problem related to control system security to attacks and provide some ways to enhance detection and awareness. More specifically, we elaborate on this issue from the control analysis, design and actual implementation point of view. We consider malicious attacks on actuators and sensors of a feedback system which can be modelled as additive, possibly unbounded, disturbances at the digital (cyber) part of the feedback loop. It is shown that the standard sampled data implementation can create additional vulnerabilities to stealthy attacks, and therefore, when security is at stake, it is of paramount importance to have methods to eliminate these vulnerabilities. By devising a multi-rate scheme we can guarantee that stealthy attacks are not possible. Further, we can provide precise trade-offs on performance and safety cost. Finally, we touch upon other type of attacks and their connections to switching systems and linear programming.
Professor Petros G. Voulgaris received the Diploma in Mechanical Engineering from the National Technical University, Athens, Greece, in 1986, and the S.M. and Ph.D. degrees in Aeronautics and Astronautics from the Massachusetts Institute of Technology in 1988 and 1991, respectively. Since 1991, he has been with the Department of Aerospace Engineering, University of Illinois where he is currently a Professor (also appointments with the Coordinated Science Laboratory, and the department of Electrical and Computer Engineering.) His research interests include optimal, robust and distributed control and estimation; networked control; applications of advanced control methods to engineering practice including, power systems, air-vehicle, nano-scale, robotic, and structural control systems. Dr. Voulgaris is a recipient of several awards including the NSF Research Initiation Award, the ONR Young Investigator Award and the UIUC Xerox Award for research. He has also been a Visiting ADGAS Chair Professor, Mechanical Engineering, Petroleum Institute, Abu Dhabi, UAE (2008-10). His research has been supported by several agencies including NSF, ONR, AFOSR, NASA, and Boeing totalling more than $12 million of funded projects. He is also a Fellow of IEEE.
Optimization in Action: Unlocking Value in the Mining, Energy, and Agriculture Industries
- 演讲人：Ryan Loxton，澳大利亚科廷大学教授／ARC Future Fellow
Mathematical optimization has numerous applications in business and industry. However, there is a large mismatch between the optimization problems studied in academia (which tend to be highly structured problems) and those encountered in practice (which are non-standard, highly unstructured problems). This talk gives an overview of the presenter’s recent experiences in building optimization models and algorithms in theoil and gas, mining, and agriculture sectors. Some of this practical work has led to academic journal articles, showing that the gap between academia and industry can be overcome.
Ryan Loxton is a full professor and ARC Future Fellow in the School of Electrical Engineering, Computing, and Mathematical Sciences at Curtin University. His work focuses on using advanced mathematics to optimise complex processes in a wide range ofapplications such as mining, oil and gas, agriculture, and industrial process control. Ryan is a passionate advocate for industry engagement and has worked with many companies including Woodside Energy, Linkforce, and Vekta Automation. He was the 2014 West Australian Young Scientist of the Yearand he currently leads the optimisation theme in the new ARC Industrial Training Centre on Transforming Maintenance through Data Science, which is funded by the Australian Research Council (the equivalent of the NSFC in Australia) and industry partners Alcoa, BHP Billiton, and Roy Hill.
World Robotic Sailing Championship
"The 3rd place of WRSC 2018 Micro-sailboat class goes to Zhejiang University! As first time participants, the made their boat within 2 months. Well done and congratulations!"
Congratulations to the ZMART / Sailing Group!
After several years explorations and research in robotics, we currently have new definition for ZMART, which was named in 2012 as ZJU's Micro-Aerial Robotics Team when we first attend the IARC (the International Aerial Robotics Competition).
In 2018, we organized two more groups to attend the other two exciting competitions, including the ICRA 2018 DJI RoboMaster AI Challenge Overview and the 11th World Robotic Sailing Championship.
Based on the new activities, the BLUe Lab is going to give a new meaning for the ZMART, ZJU's Micro Agents and Robotics Team. Then, ZMART / Aerial / Ground / Sailing represents different teams corresponding to IARC, DJI RoboMaster and WRSC, respectively.
News featured in the media include:
- 电视频道报道：国际空中机器人（IARC）大赛及青少年附加赛在中国教育电视台-1 频道播出，Youku链接
- College of Control Science & Engineering, Zhejiang University, "历时5年，浙大队ZMART勇夺国际空中机器人大赛世界冠军，终结第七代任务"
- China Automation Association (中国自动化学会), "【2018 IARC】国际空中机器人大赛将于8月26日在北京航空航天大学体育馆开幕！大赛背景介绍与参赛队伍简介一睹为快！"
- INTERNATIONAL AERIAL ROBOTICS COMPETITION Mission 7 (2014-2018), http://www.aerialroboticscompetition.org/mission7.php
- THE INTERNATIONAL AERIAL ROBOTICS COMPETITION'S 27 Year History, http://www.aerialroboticscompetition.org/pastmissions.php
"Mission 7 took a monumental leap by requiring autonomous aerial robots to interact with and control autonomous ground robots. Teams were tasked with developing systems to herd ground robots out one end of an arena in the absence of 3D cues such as walls. The ground robots could only be interacted with by touch. A top touch would command a 45° clockwise turn and a blocking action would result in a 180° turn. To complicate matters, the ground robots do a 180° turn every 20 seconds and add up to 15 degrees of trajectory noise every 5 seconds. The ground robots also impact one another and quickly devolve into non-deterministic travel. In the midst of the arena were four obstacle robots to complicate navigation and obstacle avoidance. The aerial robots had to dynamically determine a best course of action to keep the ground robots from exiting on three of four sides of the arena. In the top performances, which were replicated multiple times, the Zhejiang University team showed that its autonomous aerial robot could track individual ground robots, redirect them in either 45° or 180° increments while at the same time staying within the arena boundaries and avoiding the mobile obstacles circulating within the arena."
The First Workshop on Machine Learning, Optimization and Control
MLOC is a forum for leading researchers and industry experts on all aspects of machine intelligence and optimization, including machine learning techniques, pattern recognition, data mining, optimization theory and control techniques. In the context of this symposium, machine learning encompasses works on concurrent deep learning techniques, their associated optimization and control techniques. Given the rise of deep learning and big data analysis, the first MLOC is particularly interested in work that addresses new optimization techniques, and control tools that attempt to improve machine learning performance in big data analytics, and work towards improved industry intelligent systems.
Specific topics of interest include (but are not limited to):
- Deep learning techniques and applications
- Big data analysis
- Robust face recognition
- Data driven control
- Cyber Security
- Clustering and classification techniques
- Randomised algorithm
- Data mining and knowledge discovery
- Computer vision and image understanding
- Prof. Lei Zhang (张磊), The Hong Kong Polytechnic University
- Prof. Wanquan Liu (刘万泉), Curtin University
- Prof. Yongsheng Ou (欧勇盛), Shenzhen Institutes of Advanced Technology, CAS
- Prof. Aiguo Wu (吴爱国), Harbin Institute of Technology, Shenzhen
- Prof. Chao Xu (许超), Zhejiang University
- Zhiyang Wang
- Shichao Zhou (周世超), firstname.lastname@example.org
9:30 First Keynote
- Title: TBA (on deep learning, optimization and control in general review)
- Spekaer: Prof. Xiangchu Feng, Xidian University
10:15 Questions and Discussions
10:45 Second Keynote
- Title: Implementing the ADMM to big datasets: A case study of LASSO
- Speaker: Prof. Xiaoming Yuan, Hongkong University
11:30 Questions and Discussions
14:00 Third Keynote
- Title: Machine learning via Wasserstein statistical manifold
- Speaker: Prof. Wuchen Li, UCLA
14:45 Questions and Discussions
15:15 Fourth Keynote
- Title: TBA
- Prof. Lei Zhang, The Hong Kong Polytechnic University
16:00 Questions and Discussions
- 9:00 Title: TBA (on dictionary learning) | Speaker: Yong Xu, Harbin Institute of Technology (Shenzhen)
- 9:30 人工智能中的优化问题研究 | Lingchen Kong, Beijing Jiaotong University
- 10:00 Title: Cardiac image quantification and motion analysis based on deep neural network | Wufeng Xue, Shenzhen University
- 10:30 Title: TBA | Daoqiang Zhang (Tony), NUAA
- 11:00 Title: Computer image and image understanding | Wei Xie, South China University of Technology
- 11:30 会议结束
- 12:00 午餐
Title: Machine learning via Wasserstein statistical manifold
Abstract: In this talk, I start with reviewing several primal-dual structures in optimal transport (Wasserstein metric). Based on it, I will introduce the Wasserstein natural gradient in parametric statistical models. We pull back the L2-Wasserstein metric tensor in probability density space to parameter space, under which the parameter space become a Riemannian manifold. The gradient and Hamiltonian flows in parameter space are derived. When parameterized densities lie in 1D, we show that the induced metric tensor and gradient flow establish explicit formulas. Examples are presented to demonstrate its effectiveness in several machine learning problems.
浙江大学玉泉校区智能系统与控制研究所二楼资料室, 9 a.m., July 2, 2018
Prof. Ryan Loxton, full professor in the School of Electrical Engineering, Computing, and Mathematics at Curtin University, Australia.
Abstract: Switched systems operate by switching among various different modes. Determining the optimal times at which the mode switches should occur is a fundamental problem in systems and control, with particular importance to the numerical solution of optimal control problems. This talk will discuss the switching time optimization problem for two classes of switched systems: those with time-dependent switching conditions (where the switches are directly controllable), and those with state-dependent switching conditions (where the switches occur when the system hits certain switching surfaces in the state space). It is widely believed that standard numerical optimization techniques struggle when applied to switching time optimization problems. In this talk we present new results showing that this challenge is over-stated; contrary to popular belief, switching times can in fact be optimized effectively using standard optimization methods. We verify this with a numerical example involving a switched system model for the production of 1,3-propanediol, an industrial polymer used in paints, adhesives, and lubricants.
Bio of the speaker: Ryan Loxton is a full professor in the School of Electrical Engineering, Computing, and Mathematics at Curtin University, Australia. His research focuses on developing new mathematical techniques to optimize complex processes in a wide range of applications such as mining, oil and gas, agriculture, and industrial process control. Ryan’s work has been recognized with several high-profile awards, including two prestigious, highly competitive fellowships from the Australian Research Council and the 2014 West Australian Young Scientist of the Year Award. A passionate advocate for industry engagement, Ryan has led many industry-funded research projects with companies such as Woodside Energy, Linkforce, Roy Hill Iron Ore, Vekta Automation, and Global Grain Handling Solutions. His mathematical algorithms underpin the Quantum software system (developed by Onesun Pty Ltd) for tracking, executing, and optimizing maintenance shutdowns in the resources sector. This technology was the winner of the 2017 South32 Designing for Excellence Innovation Award. Ryan is an Associate Editor for the Journal of Industrial and Management Optimization and has published over 70 papers in international journals and conference proceedings.
Prof. Chao Xu is invited to deliver an aera talk (SS04: New Development of Smart Devices for Structural Control | 结构控制的智能装置新进展) at the 7th WCSCM, the World Conference on Structural Control and Monitoring (WCSCM). The title of Prof. Xu's talk is Infrastructure Cyber-Care: Challenges to Cyber-Systems, Robotics and Dada Analytics.
WCSCM is a premier leading conference, under the auspices of the International Association for Structural Control and Monitoring (IACSM). The WCSCM, held every four years, is aiming at promoting advanced structural control and monitoring technology for a variety of civil, mechanical, aerospace and energy systems. The precedent conferences have been held in Pasadena - USA (1994), Kyoto - Japan (1998), Como - Italy (2002), La Jolla - USA (2006), Tokyo - Japan (2010) and Barcelona - Spain (2014).The new edition of the WCSCM, 7WCSCM, will be hosted by Harbin Institute of Technology in July 2018. The conference will provide international research community a platform to contribute to the state of the art in such multidisciplinary scientific and engineering environment with new results, fresh ideas and future perspectives.
An Optimal Control Approach to Deep Learning
浙江大学玉泉校区教九101演讲厅, 9:30 a.m., June 25, 2018
Dr. Qianxiao Li, Research Scientist at the Institute of High Performance Computing, A*STAR, Singapore and an adjunct assistant professor in the department of mathematics, National University of Singapore
Abstract: In this talk, we discuss a new approach to study the algorithmic and theoretical aspects of deep learning. In particular, the optimization of deep neural networks is recast as an optimal control problem, which is a classical problem that originates from the calculus of variations. Based on this viewpoint, we investigate the development of novel algorithms, as well as theoretical insights on generalization bounds of neural networks.
Bio of the speaker: Qianxiao Li is a research Scientist at the Institute of High Performance Computing, A*STAR, Singapore and an adjunct assistant professor in the department of mathematics, National University of Singapore. He graduated with a BA in Mathematics from University of Cambridge in 2010, and a PhD in applied mathematics from Princeton University in 2016. His main research interests include the theory and algorithms for deep learning, stochastic optimization and applications ofmachine learning to the physical sciences.