BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系 - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
X-ORIGINAL-URL:https://ece.hku.hk
X-WR-CALDESC:Events for Department of Electrical and Computer Engineering (HKUECE) 電機與計算機工程系
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Asia/Hong_Kong
BEGIN:STANDARD
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
TZNAME:HKT
DTSTART:20240101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20251125T080000
DTEND;TZID=Asia/Hong_Kong:20251125T090000
DTSTAMP:20260511T143725
CREATED:20251120T081820Z
LAST-MODIFIED:20251120T081820Z
UID:114045-1764057600-1764061200@ece.hku.hk
SUMMARY:RPG Seminar – An Acoustic-responsive Hydrogel Electrode for Wearable Deep Brain Stimulation
DESCRIPTION:Zoom Link: https://hku.zoom.us/j/94612024859?pwd=Sqldxnoy6vEOP3HqfBBLs1oMxAQvFx.1 \nAbstract\nDeep brain stimulation (DBS) is a powerful therapy for neurological disorders\, yet conventional systems rely on finite-lifetime batteries and rigid implants that necessitate repeated surgeries and pose long-term risks. This seminar presents EchoGel\, a brain-compatible\, acoustic-responsive\, and conductive hydrogel electrode platform designed to enable fully wearable\, battery-free DBS. Once implanted in the brain\, EchoGel harvests external acoustic waves to enable wireless energy transfer and eliminate tethered connections. Its flexible\, needle-shaped hydrogel electrodes then provide stable and long-lasting stimulation. When integrated with a miniaturized wearable acoustic generator\, the system delivers deeper and more durable neuromodulation in freely behaving animals. Together\, these advances establish a path toward safer\, minimally invasive\, and long-lasting DBS technologies. \nSpeaker\nMs. Yilin Yang\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nBiography of the Speaker\nYilin Yang received her B.Eng. and M.Eng\, both in Biomedical Engineering from Sun Yat-sen University. She is currently a Ph.D. student in the WISE Research Group working on brain-machine interfacing with soft and implantable bioelectronic systems. She is interested in the design\, fabrication\, and characterization of wearable neuromodulation and recording system based on novel soft materials. \nOrganiser\nProf. Shiming Zhang\nDepartment of Electrical and Electronic Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20251125-5/
LOCATION:Online via Zoom
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20251125T140000
DTEND;TZID=Asia/Hong_Kong:20251125T150000
DTSTAMP:20260511T143725
CREATED:20251117T063039Z
LAST-MODIFIED:20251117T063039Z
UID:113905-1764079200-1764082800@ece.hku.hk
SUMMARY:RPG Seminar – Robot Learning and Control for Fabric Manipulation and Fixture-Free Automated Sewing
DESCRIPTION:Zoom Link: https://hku.zoom.us/j/7425733217?omn=96993354197 \nAbstract\nAutomating garment production requires production‑grade precision for each production process across diverse fabrics\, which remains challenging for conventional model-based methods. While model-based control scheme is effective for automating rigid-body handling processes\, it struggles with fabrics’ effectively infinite degrees of freedom\, nonlinear dynamics\, and frequent self-occlusions from wrinkles and folds. End‑to‑end deep learning offers rich representational power to capture fabric states and dynamics for policy learning\, yet existing methods lack the precision\, stability\, and safety guarantees demanded by industrial deployment. \nTo address this challenge\, we present a new robot learning and control paradigm for fabric manipulation in which learning expands the boundary of achievable tasks\, while control guarantees system stability and performance. The paradigm comprises: (i) multi-level perception\, (ii) feedback-structured policy learning\, and (iii) convergence-and-stability assurance. \nWe instantiate this paradigm in fixture-free sewing with a dual-arm manipulator and an ordinary industrial sewing machine. \n\nThe multi-level perception comprises global fabric state estimation using a mesh-based representation with a Graph Attention Network (GAT) and local\, real-time edge detection using High-speed Fabric Edge Detection System (Hi-FEDS)\, enabling global pose tracking\, wrinkle-aware state representation\, and precise seam estimation for real-time sewing.\nThe feedback‑structured policy learning—implemented via Imitation Learning (IL) with the Mesh Action Chunking Transformer (MACT)—operates in a closed‑loop\, error‑driven fashion to drive random wrinkled fabrics toward wrinkle‑free target states.\nOnce the fabrics reach control‑ready initial states\, a model‑based nonlinear controller—using nonholonomic sewing dynamics and time scaling—guarantees exponential convergence and sub‑millimeter steady‑state sewing error. Dual‑arm impedance control regulates internal wrenches applied to the fabric and the external wrenches of the system\, ensuring stability when interacting with passive environments.\n\nSpeaker\nMr. Kai Tang\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nBiography of the Speaker\nKai Tang received his B.Sc. in Process Equipment and Control Engineering from South China University of Technology in 2020\, and M.Sc. (Distinction) in Control and Optimisation from Imperial College London in 2021. He is currently pursuing Ph.D. in robotics at JC STEM Lab of Robotics for Soft Materials\, the Department of Electrical and Electronic Engineering\, The University of Hong Kong. He is involved in the Centre for Transformative Garment Production\, Hong Kong SAR. His research focuses on robotic fabric manipulation and fixture-free automated sewing using control and deep learning. \nOrganiser\nProf. Kazuhiro Kosuge\nDepartment of Electrical and Electronic Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20251125/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20251125T150000
DTEND;TZID=Asia/Hong_Kong:20251125T160000
DTSTAMP:20260511T143725
CREATED:20251118T034820Z
LAST-MODIFIED:20251118T035127Z
UID:113916-1764082800-1764086400@ece.hku.hk
SUMMARY:RPG Seminar – Seam-Informed Garment Handling Using Bimanual Manipulator
DESCRIPTION:Zoom Link: https://hku.zoom.us/j/7425733217?omn=96993354197 \nAbstract\nSeams are information-rich components of garments. The presence and combination of different types of seam help to estimate the state of a garment. We introduce a novel Seam-Informed Strategy (SIS) for garment state estimation and planning for garment handling.  In this talk\, we will consider a problem to flatten a T-shirt which is randomly placed on a flat surface and demonstrate how SIS effectively estimate the garment state to facilitate grasp and unfold action. \nSeams are extracted from visual information. The Seam Feature Extraction Method is proposed to formulate seam extraction as an oriented object detection problem. The extracted seams provide an implicit representation of the garment’s structure and are used as grasping point candidates for bimanual flinging to unfold the garment. The Decision Matrix Iteration Method is proposed to select a pair of grasping points from the grasping point candidates. The decision matrix is initialized based on human demonstrations\, then updated using the robot’s execution results to improve its grasping and unfolding policy. Experimental results demonstrate the effectiveness and generalization ability of the proposed strategy. \nSpeaker\nMr. Xuzhao Huang\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nBiography of the Speaker\nXuzhao Huang received the B.Eng. degree in Mechanical Design\, Manufacturing\, and Automation from Xiamen University\, China\, in 2018\, and the M.Eng. degree in Mechatronics Engineering from the Harbin Institute of Technology\, Shenzhen\, in 2021. He is currently pursuing the Ph.D. degree in Engineering with The University of Hong Kong. His research interests include visual perception and robotic manipulation of deformable objects. \nOrganiser\nProf. Kazuhiro Kosuge\nDepartment of Electrical and Electronic Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20251125-2/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20251125T150000
DTEND;TZID=Asia/Hong_Kong:20251125T160000
DTSTAMP:20260511T143725
CREATED:20251119T064431Z
LAST-MODIFIED:20251119T064939Z
UID:114022-1764082800-1764086400@ece.hku.hk
SUMMARY:RPG Seminar – Diffusion Model Acceleration with RRAM-based In-memory Neural Differential Equation Solver
DESCRIPTION:Zoom Link: https://hku.zoom.us/j/93740801215 \nAbstract \nDiffusion models generate high-quality images and videos\, closely mirroring the imagination of human brain. Specifically\, score-based diffusion models generate by solving neural differential equations. However\, their digital computer implementations are discrete in time and inherently digital\, with energy efficiency constrained by the von Neumann architecture. Herein\, we firstly demonstrate a chip-level solution that embodies the implementation of time-continuous and analog conditional score-based diffusion using a Resistive Random Access Memory (RRAM) in-memory neural differential equation solver. Notably\, the score-based diffusion process is intrinsically robust to analog computing noise. We validate our solution on a conditional diffusion task. Our in-memory neural differential equation solver opens a brand-new hardware solution for edge generative AI. \nSpeaker\nMr. Jichang Yang\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nBiography of the Speaker\nJichang Yang received both his B.Sc. and M.Sc. from the School of Electrical and Electronic Engineering at Huazhong University of Science and Technology\, Wuhan\, China\, in 2019 and 2022\, respectively. He is currently pursuing the Ph.D. degree with the Department of Electrical and Electronic Engineering under the supervision of Prof. Han Wang. His research interests mainly include in-memory computing\, diffusion models\, and software-hardware co-design. \nOrganiser\nProf. Han Wang\nDepartment of Electrical and Electronic Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20251125-4/
LOCATION:Online via Zoom
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Asia/Hong_Kong:20251125T160000
DTEND;TZID=Asia/Hong_Kong:20251125T170000
DTSTAMP:20260511T143725
CREATED:20251118T035502Z
LAST-MODIFIED:20251118T035502Z
UID:113919-1764086400-1764090000@ece.hku.hk
SUMMARY:RPG Seminar – Automated Straight-line Sewing of Stretchable Fabrics with Different Lengths
DESCRIPTION:Zoom Link: https://hku.zoom.us/j/7425733217?omn=96993354197 \nAbstract\nDifferent Length Alignment Sewing (DLAS)\, which involves stretching the shorter fabric to match the longer one and sewing them together in a straight line\, is a challenging task that needs to satisfy several requirements when automating the sewing process. To address the challenges\, we propose a novel robotic sewing system\, Different Length Robotic Sewing System (DLRoSS)\, which consists of a roller type end-effector\, attached to a 6-DoF manipulator. The end-effector composed of active shorter and longer fabric rollers\, and a passive press-roller attached to the shorter-fabric roller. Assuming that one end of the two fabric layers are initially positioned under the sewing machine’s presser foot\, the system automates DLAS by operating in four distinct phases. (P1) Fabric wrapping: Individual fabric layers are picked\, held\, and wrapped from the other end onto the feed rollers. (P2) Sewing: During the sewing\, the shorter fabric is stretched and aligned with the longer fabric in real- time using roller velocity control based on the sewing speed and apriori known length ratio. (P3) Sewing completion: In the final sewing round on the fabric rollers\, the press roller is engaged to prevent the stretched fabric from slipping off due to internal tension. (P4) Sewing fabric release: At the end of sewing\, the fabric edge moves past the press roller\, and the fabric releases from the rollers. Experimental results demonstrate that DLRoSS achieves consistent\, high-quality sewing of stretchable fabrics of different materials and lengths. \n \nSpeaker\nMr. Bingchen Jin\nDepartment of Electrical and Electronic Engineering\nThe University of Hong Kong \nBiography of the Speaker\nBingchen Jin received his B.Sc. degree in Mechanics and Electronics Engineering from Jiangsu University\, China\, in 2015\, and his M.Sc. degree in Mechanical Engineering from Harbin Institute of Technology (Shenzhen)\, in 2018. From 2019 to 2021\, he was a research assistant in the Chinese University of Hong Kong (Shenzhen). He is currently towards his Ph.D. degree at the Department of Electrical and Electronic Engineering\, The University of Hong Kong\, Hong Kong SAR. He is involved in the Centre for Transformative Garment Production\, Hong Kong SAR. His research focuses on robotics manipulation\, and artificial intelligence. \nOrganiser\nProf. Kazuhiro Kosuge\nDepartment of Electrical and Electronic Engineering\, The University of Hong Kong \nAll are welcome.
URL:https://ece.hku.hk/events/20251125-3/
LOCATION:Room CB-603\, 6/F\, Chow Yei Ching Building\, The University of Hong Kong
CATEGORIES:Seminar
ATTACH;FMTTYPE=image/jpeg:https://ece.hku.hk/wp-content/uploads/2024/11/rpg-seminar.jpg
END:VEVENT
END:VCALENDAR