Prof. Danica Kragic
Royal Institute of Technology (KTH), Sweden
Biodata: Danica Kragic is a Professor at the School of Computer Science and Communication at the Royal Institute of Technology, KTH. She received MSc in Mechanical Engineering from the Technical University of Rijeka, Croatia in 1995 and PhD in Computer Science from KTH in 2001. She has been a visiting researcher at Columbia University, Johns Hopkins University and INRIA Rennes. She is the Director of the Centre for Autonomous Systems. Danica received the 2007 IEEE Robotics and Automation Society Early Academic Career Award. She is a member of the Royal Swedish Academy of Sciences, Royal Swedish Academy of Engineering Sciences and Young Academy of Sweden. She holds a Honorary Doctorate from the Lappeenranta University of Technology. She chaired IEEE RAS Technical Committee on Computer and Robot Vision and served as an IEEE RAS AdCom member. Her research is in the area of robotics, computer vision and machine learning. In 2012, she received an ERC Starting Grant. Her research is supported by the EU, Knut and Alice Wallenberg Foundation, Swedish Foundation for Strategic Research and Swedish Research Council. She is an IEEE Fellow.
Speech Title: Representation Learning for Robotics Tasks
Abstract: All day long, our fingers touch, grasp and move objects in various media such as air, water, oil. We do this almost effortlessly - it feels like we do not spend time planning and reflecting over what our hands and fingers do or how the continuous integration of various sensory modalities such as vision, touch, proprioception, hearing help us to outperform any other biological system in the variety of the interaction tasks that we can execute. Largely overlooked, and perhaps most fascinating is the ease with which we perform these interactions resulting in a belief that these are also easy to accomplish in artificial systems such as robots. However, there are still no robots that can easily hand-wash dishes, button a shirt or peel a potato. Our claim is that this is fundamentally a problem of appropriate representation or parameterization. When interacting with objects, the robot needs to consider geometric, topological, and physical properties of objects. This can be done either explicitly, by modeling and representing these properties, or implicitly, by learning them from data. The main objective of our work is to create new informative and compact representations of deformable objects that incorporate both analytical and learning-based approaches and encode geometric, topological, and physical information about the robot, the object, and the environment. We do this in the context of challenging multimodal, bimanual object interaction tasks. The focus will be on physical interaction with deformable and soft objects.
Prof. Fuchun Sun 孙富春
Tsinghua University, China 清华大学
Biodata: Dr. Fuchun Sun is
professor of Department of Computer Science and Technology
and President of Academic Committee of the Department,
Tsinghua University, deputy director of State Key Lab. of
Intelligent Technology & Systems, Beijing, China. He also
serve as Vice president of China Artificial Intelligence
Society and executive director of China Automation Society.
His research interests include robotic perception and
intelligent control. He has won the Champion of Autonoumous
Grasp Challenges in IROS2016 and IROS 2019.
Dr. Sun is the recipient of the excellent Doctoral Dissertation Prize of China in 2000 by MOE of China and the Choon-Gang Academic Award by Korea in 2003, and was recognized as a Distinguished Young Scholar in 2006 by the Natural Science Foundation of China. He served as an associated editor of IEEE Trans. on Neural Networks during 2006-2010, IEEE Trans. On Fuzzy Systems during 2011-2018, IEEE Trans. on Cognitive and Developement since 2018 and IEEE Trans. on Systems, Man and Cybernetics: Systems since 2015.
孙富春，清华大学计算机科学与技术系教授，博士生导师，清华大学校学术委员会委员，计算机科学与技术系学术委员会主席，智能技术与系统国家重点实验室常务副主任。兼任担任国家863计划专家组成员，国家自然基金委重大研究计划“视听觉信息的认知计算”指导专家组成员，中国人工智能学会认知系统与信息处理专业委员会主任，中国自动化学会认知计算与系统专业委员会主任，国际刊物《IEEE Trans. on FuzzySystems》，《IEEETrans. on Systems, Man and Cybernetics: Systems》《Mechatronics》和《International Journalof Control, Automation, and Systems (IJCAS)》副主编或领域主编，国际刊物《Robotics andAutonumous Systems》和《InternationalJournal of Computational Intelligence Systems》编委，国内刊物《中国科学：F辑》和《自动化学报》编委。 98年3月在清华大学计算机应用专业获博士学位。98年1月至2000年1月在清华大学自动化系从事博士后研究，2000年至今在计算机科学与技术系工作。工作期间获得的主要奖励有：2000年全国优秀博士论文奖，2001年国家863计划十五年先进个人，2002年清华大学“学术新人奖”，2003年韩国第十八届Choon-Gang 国际学术奖一等奖第一名，2004年教育部新世纪人才奖，2006年国家杰出青年基金。获奖成果6项，两项成果获2010年教育部自然科学奖二等奖（排名第一）和2004年度北京市科学技术奖（理论类）二等奖（排名第一）、一项获2002年度教育部提名国家科技进步二等奖（排名第二）、四项获省部级科技进步三等奖。译书一部，专著两部，在国内外重要刊物发表或录用论文150余篇，其中在IEE、IEEE汇刊、Automatica等国际重要刊物发表论文90余篇，有两篇论文曾被评为国内二级学会的最佳优秀论文奖。
Speech Title: Skill Learning in Dynamic Scene for Robot Operations
Abstract: The robot AI is dominated by physical interaction in closed-loop form. It not only emphasizes the perception and processing of simulated human brain information, but also emphasizes brain body cooperation to solve the dynamic, interactive and adaptive problems of behavior learning in dynamic scene. As the core of robot AI, skill learning for robot operations is a difficult and hot issue in current research. In view of the problems that the existing skill learning methods do not make use of the teaching samples efficiently and cannot achieve efficient strategy learning, and the imitation learning algorithm is sensitive to the teaching preference characteristics and the local operation space. This talk studies the skill learning for robot operations in the complex dynamic environment, and proposes skill learning framework based on human preference. By using the guidance of the existing poor teaching samples, this talk proposes an optimization method of reinforcement learning based on teaching imitation, which improves the sample utilization rate and strategy learning performance of skill learning in high-dimensional space. Finally, the future development of robot skill learning is prospected.
Prof. Maria Pia Fanti
Polytechnic University of Bari, Italy
Biodata: Maria Pia Fanti
(fellow of IEEE) received the Laurea degree in electronic
engineering from the University of Pisa, Pisa, Italy, in
1983. She was a visiting researcher at the Rensselaer
Polytechnic Institute of Troy, New York, in 1999. Since
1983, she has been with the Department of Electrical and
Information Engineering of the Polytechnic of Bari, Italy,
where she is currently a Full Professor of system and
control engineering and Chair of the Laboratory of
Automation and Control.
Her research interests include modeling and control of complex systems, intelligent transportation systems, smart logistics; Petri nets; consensus protocols; fault detection.
Prof. Fanti has published more than +300 papers and two textbooks on her research topics. She was senior editor of the IEEE Trans. on Automation Science and Engineering and member at large of the Board of Governors of the IEEE Systems, Man, and Cybernetics Society. Currently, she is Associate Editor of the IEEE Trans. on Systems, Man, and Cybernetics: Systems, member of the AdCom of the IEEE Robotics and Automaton Society, and chair of the Technical Committee on Automation in Logistics of the IEEE Robotics and Automation Society. Prof. Fanti was General Chair of the 2011 IEEE Conference on Automation Science and Engineering, the 2017 IEEE International Conference on Service Operations and Logistics, and Informatics and the 2019 Systems, Man, and Cybernetics Conference.
Prof. Aiguo Song 宋爱国教授 （国家杰出青年基金获得者、入选中国工程院2021年院士增选有效候选人名单）
Southeast University, China 东南大学
(IEEE Senior Member)
Biodata: Aiguo Song
received the Ph.D degree in Measurement and Control from
Southeast University, Nanjing, China in 1996. From 1996 to
1998, he was an Associate Researcher with the Intelligent
Information Processing Laboratory, Southeast University,
China. From 1998 to 2000, He was an associate Professor with
the School of Instrument Science and Engineering, Southeast
University, China. From 2000 to 2003, he was the Director of
the Robot Sensor and Control Lab, Southeast University,
China. From April, 2003 to April, 2004, he was a visiting
scientist with the Lab for Intelligent Mechanical Systems
(LIMS), Northwestern University, Evanston, USA. He is
currently the Professor with the School of Instrument
Science and Engineering, Southeast University, China, and
also the Director of Robot Sensor and Control Laboratory,
the President of Nanjing Advanced Robotics Research
Institute. His current interests concentrate on human-robot
interaction teleoperation robot, force/tactile sensors,
haptic display, space robot, and rehabilitation robot. He
has published more than 280 peer reviewed journal papers,
and 180+ papers have been indexed by SCIE, and SCI cited
time is 2000+. He received the best paper awards 12 times.
He is a member of Chinese Instrument and Control
Association, IEEE senior member, Chair of IEEE Nanjing
Section Robotics and Automation Society Chapter. He serves
as Associate Editor for 5 SCIE indexed Journals, and served
as Chair or Co-Chair of 30+ International
Conference/Symposium. He was recipient of the second prize
of the National Scientific and Technological Progress in
2017, and recipient of the National Outstanding Youth Fund
of National Natural Science Foundation of China.
Prof. Zunfeng Liu 刘遵峰教授
Nankai University, China 南开大学
Biodata: Zunfeng Liu has
published over 80 peer reviewed SCI papers and cited for
over 13000 times by other researchers, including Science,
Adv. Mater., Adv. Funct. Mater., etc. He received his BS and
PhD in Polymer Chemistry from Nankai University (China) in
2002 and 2008, respectively. From 2008 to 2013, he was
working as a postdoc fellow and project leader in Erasmus
Medical center, Leiden University (Netherlands). From 2013
to 2016, he was a professorship in Changzhou University. He
joint Nankai University as a full professor in June 2016.
Zunfeng’s current research interests are elastic and
flexible devices, artificial muscles, wearable electronics
and sensors. He has given over 40 plenary or invited talks
in national and international conferences in the field of
smart flexible materials.
刘遵峰，南开大学特聘研究员。研究方向为：仿生智能高分子材料，包括高强韧人造蜘蛛丝、人工肌肉、柔性电子、柔性制冷等。在 Science , Nat. Commun., Adv. Mater.等国际学术 SCI 期刊上发表研究论文 80 余篇。其中2015年关于可拉伸导体的研究工作被美国《Discover Magazine》评选为2015年度全球TOP100重大科学发现；2019年关于“扭热制冷”的工作开创了新型固态柔性制冷新方法，大幅提高了制冷效率；研发的水凝胶纤维人造蜘蛛丝强度与韧性性能接近天然蜘蛛丝；基于蚕丝、棉纤维、竹纤维、动物毛等发展了多种智能织物。多篇关于柔性健康监测的文章被选为封面文章，受邀撰写多篇综述，申请中国专利20余项，在多个国内外学术会议做邀请报告40余次。入选国家高层次青年人才支持计划，获得天津市杰出青年基金，第十二届江苏省优秀科技工作者等荣誉称号。网址：https://liuzunfeng.nankai.edu.cn
Speech Title: Periodic
Curved Fiber Materials for Smart Materials-Artificial Muscles,
Artificial Spider Silk, Flexible Electronics, and Twistocaloric
Abstract: Functional polymer
fibers show promising mechanical, thermal, and electrical
properties, and may find important applications in wearable
electronics, cooling, and tough fibers. Here by mimicking the
nature, we designed functional fiber materials with periodical
geometrical structures, such as twisting, coiling, and buckling.
These fiber materials exhibit interesting properties, due to the
periodical twisting, coiling, and buckling of the macromolecular
chains. (1) We prepared artificial spider silks by using
“twisted sheath-core” hydrogel fibers with chemical and physical
cross-linking points, whose mechanical strength and toughness
are close to those of the natural spider silk. (2) Twist
insertion in natural fiber materials e.g. silkworm silk, cotton,
bamboo fiber, hair fiber produces moisture driven artificial
muscles, which can rotate, contract, and elongate in response to
moisture. (3) Inserting twist highly improved the cooling
efficiency of elastomer fibers from 32% to 67%, and rigid
polymer fibers also show high cooling temperature by twist
insertion. (4) We prepared highly elastic conductive fibers by
using buckled conductive layer with zero-Poison’s ratio,
realizing ultra-stable resistance during large elongation. (5)
Based on the above periodical structures, we designed
multi-functional materials with hierarchical geometrical
structures, realizing strain sensors, artificial muscles, and