报告时间：8月28日（周四）下午3：30
报告地点：信息楼316
（一）
报告题目：基于人类模仿的机器人控制（Robot Control by Learning from Humans）
报告人简介：
Professor Chenguang Yang holds the Chair in Robotics in the Department of Computer Science at the University of Liverpool, UK, where he leads the Robotics and Autonomous Systems Group. He is a member of European Academy of Sciences and Arts, and he is also recognized as a Fellow by several prestigious institutions, including the Institute of Electrical and Electronics Engineers (IEEE), Institute of Engineering and Technology (IET), Institution of Mechanical Engineers (IMechE), Asia-Pacific AI Association (AAIA), and British Computer Society (BCS). Professor Yang serves as the corresponding Co-Chair of the IEEE Technical Committee on Collaborative Automation for Flexible Manufacturing (CAFM). He previously served as President of the Chinese Automation and Computing Society in the UK (CACSUK) and has organized several conferences as the general chair, includingthe 25th IEEE International Conference on Industrial Technology (ICIT) and the 27th International Conference on Automation and Computing (ICAC). As the lead author, he received the prestigious IEEE Transactions on Robotics Best Paper Award in 2012 and the IEEE Transactions on Neural Networks and Learning Systems Outstanding Paper Award in 2022.
内容简介：
This presentation will provide a broad overview of my research in robotics with a focus on learning from Demonstration (LfD). LfD allows robots to acquire and generalize task skills through human demonstrations, creating a seamless integration of artificial intelligence and robotics. Most LfD approaches often overlook the importance of demonstrated forces and rely on manually configured impedance parameters. In response, my team has developed a series of biomimetic impedance and force controllers inspired by neuroscientific findings on motor control mechanisms in humans, enabling robots to imitate compliant manipulation skills. The presentation also covers collaborative control strategies for human-robot interaction, and long-horizon manipulation based on subgoal planning. Tactile sensing designs, soft gripper designs, perception and mapping methods, and advancements in dynamic SLAM and object tracking are also included. Particularly, we designed anthropomorphic visual tactile sensors that assess contact force, surface texture, and shape, to improve robot skill learning through enhanced perceptual capabilities.
（二）
报告题目：智能材料驱动器中迟滞非线性的建模与控制（Modelling and Control of Hysteresis Nonlinearities in Smart Actuators）
报告人简介：
Dr Wenjun Ye received his PhD and MASc degrees in Mechanical Engineering from Concordia University, Canada, in 2016 and 2023, respectively. He also obtained a BE in Naval and Ocean Engineering from Shanghai Jiao Tong University in 2012. From 2023 to 2024, he worked as a Postdoctoral Research Associate at the University of Manchester, UK. Since 2024, he has been a Lecturer in the Department of Computer Science at the University of Liverpool, UK. Dr Ye’s research interests include exoskeleton robotics, smart material-enabled actuators and intelligent control.
内容简介：
Smart actuators, characterised by high energy densities, large strokes and rapid responses, are playing an increasingly important role in micro- and nano-positioning applications. However, hysteresis nonlinearities are a common feature of actuators based on smart materials. For decades, these nonlinearities have posed one of the most difficult challenges for control design engineers, since both Laplace-domain and most state-space control design techniques were originally developed exclusively for differentiable linear or nonlinear systems. Consequently, traditional controllers were often designed under the assumption that hysteresis effects in practical systems could be neglected. When actuators exhibiting hysteresis are taken into account, these methods face significant difficulties during analysis, model identification and control design. In many cases, designing such systems—or proving their stability—has been extremely difficult, if not impossible. The development of techniques to identify these nonlinearities in smart material-based actuators has therefore emerged as a significant research problem in its own right.
This talk will present and discuss state-of-the-art solutions for the modelling and control of hysteresis effects in smart actuators. The scope of the presentation will range from hysteresis modelling approaches to the design of suitable control schemes, with particular emphasis on cases where complete information about the system model and states is unavailable.