Shuangyue Yu

ORCID: 0000-0003-1673-0844
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Prosthetics and Rehabilitation Robotics
  • Muscle activation and electromyography studies
  • Stroke Rehabilitation and Recovery
  • Robot Manipulation and Learning
  • Soft Robotics and Applications
  • Spinal Cord Injury Research
  • Machine Learning and ELM
  • Mechanical Circulatory Support Devices
  • Aortic Disease and Treatment Approaches
  • Dielectric materials and actuators
  • Balance, Gait, and Falls Prevention
  • Neural Networks and Applications
  • Robotic Locomotion and Control
  • Cerebral Palsy and Movement Disorders
  • Reinforcement Learning in Robotics
  • Advanced Algorithms and Applications
  • Fault Detection and Control Systems
  • AI-based Problem Solving and Planning
  • Face and Expression Recognition
  • Iterative Learning Control Systems
  • Modular Robots and Swarm Intelligence
  • Robotics and Sensor-Based Localization
  • Advanced Materials and Mechanics
  • Gait Recognition and Analysis
  • Hand Gesture Recognition Systems

Beijing University of Technology
2024-2025

New York University
2025

North Carolina State University
2021-2024

City College of New York
2018-2021

City University of New York
2018-2021

City College
2018-2020

High-performance actuators are crucial to enable mechanical versatility of wearable robots, which required be lightweight, highly backdrivable, and with high bandwidth. State-of-the-art actuators, e.g., series elastic have compromise bandwidth improve compliance (i.e., backdrivability). In this article, we describe the design human-robot interaction modeling a portable hip exoskeleton based on our custom quasi-direct drive actuation torque density motor low ratio gear). We also present...

10.1109/tmech.2020.2995134 article EN publisher-specific-oa IEEE/ASME Transactions on Mechatronics 2020-05-18

This letter presents design principles for comfort-centered wearable robots and their application in a lightweight backdrivable knee exoskeleton. The mitigation of discomfort is treated as mechanical control issues three solutions are proposed this letter: 1) new structure optimizes the strap attachment configuration suit layout to ameliorate excessive shear forces conventional design; 2) rolling joint double-hinge mechanisms reduce misalignment sagittal frontal plane, without increasing...

10.1109/lra.2018.2864352 article EN IEEE Robotics and Automation Letters 2018-08-08

Back injuries are the most prevalent work-related musculoskeletal disorders and represent a major cause of disability. Although innovations in wearable robots aim to alleviate this hazard, majority existing exoskeletons obtrusive because rigid linkage design limits natural movement, thus causing ergonomic risk. Moreover, these systems typically only suitable for one type movement assistance, not ubiquitous wide variety activities. To fill gap, letter presents new robot approach continuum...

10.1109/lra.2019.2935351 article EN publisher-specific-oa IEEE Robotics and Automation Letters 2019-08-14

State-of-the-art exoskeletons are typically limited by the low control bandwidth and small-range stiffness of actuators, which based on high gear ratios elastic components (e.g., series actuators). Furthermore, most discrete gait phase detection and/or control, resulting in discontinuous torque profiles. To fill these two gaps, we developed a portable, lightweight knee exoskeleton using quasi-direct-drive (QDD) actuation that provides 14 N·m (36.8% biological joint moment for overground...

10.1109/tro.2022.3170287 article EN IEEE Transactions on Robotics 2022-06-01

This letter presents design and control innovations of wearable robots that tackle two barriers to widespread adoption powered exoskeletons: restriction human movement versatile co-robot systems. First, the proposed high torque density actuation comprised our customized high-torque motors low ratio transmission mechanism significantly reduces mass robot produces backdrivability. Second, we derive a biomechanics model-based generates assistive profile for both squat stoop lifting assistance....

10.1109/lra.2019.2931427 article EN publisher-specific-oa IEEE Robotics and Automation Letters 2019-07-26

Mechanical computing encodes information in deformed states of mechanical systems, such as multistable structures. However, achieving stable memory most systems remains challenging and often limited to binary information. Here, we report leveraging coupling kinematic bifurcation rigid cube-based mechanisms with elasticity create transformable, metastructures stable, high-density memory. Simply stretching the planar metastructure forms a corrugated platform. It allows for independent or...

10.1126/sciadv.ado6476 article EN cc-by-nc Science Advances 2024-06-26

Construction workers regularly perform tasks that require kneeling, crawling, and squatting. Working in awkward kneeling postures for prolonged time periods can lead to knee pain, injuries, osteoarthritis. In this article, we present lightweight, wearable sensing, assistive devices construction during squatting tasks. Analysis of on level sloped surfaces (0 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">°</sup> , 10 20 ) is performed single-...

10.1109/tmech.2021.3081367 article EN publisher-specific-oa IEEE/ASME Transactions on Mechatronics 2021-05-18

High-performance prostheses are crucial to enable versatile activities like walking, squatting, and running for lower extremity amputees. State-of-the-art either not powerful enough support demanding or have low compliance (low backdrivability) due the use of high speed ratio transmission. Besides ratio, gearbox design is also wearable robots, but its role typically ignored in process. This paper proposed an analytical backdrive torque model that accurately estimate from both motor...

10.1109/tmech.2022.3176255 article EN publisher-specific-oa IEEE/ASME Transactions on Mechatronics 2022-06-03

This paper presents the design and evaluation of a soft hand exo-sheath integrated with fabric electromyography (EMG) sensor for rehabilitation activities daily living (ADL) assistance stroke spinal cord injury (SCI) patients. wearable robot addresses limitations gloves considerations in terms ergonomics clinical practice. Its features include: this is based on electric actuation has been designed to be compact portable. It reduces shear force avoids kinematic singularity comparing...

10.1109/robosoft.2018.8405375 article EN 2018-04-01

This paper presents a portable inertial measurement unit (IMU)-based motion sensing system and proposed an adaptive gait phase detection approach for non-steady state walking multiple activities (walking, running, stair ascent, descent, squat) monitoring. The algorithm aims to overcome the limitation of existing methods that are time-domain thresholding based steady-state not versatile detect during different or patterns same activity. suit is composed three IMU sensors (wearable detection)...

10.1115/dmd2019-3266 article EN 2017 Design of Medical Devices Conference 2019-04-15

Fluid‐driven artificial muscles exhibit a behavior similar to biological which makes them attractive as soft actuators for wearable assistive robots. However, state‐of‐the‐art fluidic systems typically face challenges meet the multifaceted needs of First, robots are usually constrained tethered pressure sources or bulky configurations based on flow control valves delivery and high forces. Second, although some untethered operation, they significantly limited low force capabilities. Herein,...

10.1002/aisy.202400171 article EN cc-by Advanced Intelligent Systems 2024-06-13

Powered knee exoskeletons have shown potential for mobility restoration and power augmentation. However, the benefits of are partially offset by some design challenges that still limit their positive effects on people. Among them, joint misalignment is a critical aspect mostly because human movement not fixed-axis rotation. In addition, remarkable mass stiffness also limitations. Aiming to minimize misalignment, this paper proposes bio-inspired exoskeleton with mimics joint. Moreover,...

10.3389/fnhum.2022.1018160 article EN cc-by Frontiers in Human Neuroscience 2022-11-07

Abstract The positional information of objects is crucial to enable robots perform grasping and pushing manipulations in clutter. To effectively manipulations, need perceive the position objects, including coordinates spatial relationship between (e.g., proximity, adjacency). authors propose an end‐to‐end position‐aware deep Q‐learning framework achieve efficient collaborative Specifically, a pair conjugate attention modules are proposed capture generate high‐quality affordance maps...

10.1049/cit2.12264 article EN cc-by CAAI Transactions on Intelligence Technology 2023-08-02

Individuals with spinal cord injury (SCI) and stroke who is lack of manipulation capability have a particular need for robotic hand exoskeletons. Among assistive rehabilitative medical exoskeletons, there exists sharp trade-off between device power on the one ergonomics portability other, devices that provide stronger grasping assistance do so at cost patient comfort. This paper proposes using fin-ray-inspired, cable-driven finger orthoses to generate high fingertip forces without painful...

10.1115/dmd2019-3268 article EN 2017 Design of Medical Devices Conference 2019-04-15

Abstract Individuals with foot drop caused by stroke or cerebral palsy (CP) have a particular need for robotic ankle exoskeleton. This paper proposes an untethered soft robot using origami actuator to lift the toes of wearer. The weight, connections, and complex control system are reduced through mechanical design. A compact portable pneumatic is designed perform suction compression single pump. load test shows capability 300N in 30 kPa. An untethered, simple affordable exoskeleton developed...

10.1115/dmd2020-9099 article EN 2017 Design of Medical Devices Conference 2020-04-06

<title>Abstract</title> Our experimental protocol details the human subject evaluation of a novel, simulation-based approach for optimizing exoskeleton control strategies. Utilizing multi-layer perceptron neural networks, this achieves: modeling kinematics, muscle coordination, and automating assistance. This method capitalizes on strengths data-driven machine learning to refine strategies, significantly reducing metabolic costs across various activities including walking, running, stair...

10.21203/rs.3.pex-2632/v1 preprint EN Research Square (Research Square) 2024-04-26
Coming Soon ...