Yu She

ORCID: 0000-0001-5914-3573
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Robot Manipulation and Learning
  • Soft Robotics and Applications
  • Tactile and Sensory Interactions
  • Prosthetics and Rehabilitation Robotics
  • Muscle activation and electromyography studies
  • Space Satellite Systems and Control
  • Advanced Sensor and Energy Harvesting Materials
  • Modular Robots and Swarm Intelligence
  • Dynamics and Control of Mechanical Systems
  • Reinforcement Learning in Robotics
  • Robotic Mechanisms and Dynamics
  • Robotic Locomotion and Control
  • Interactive and Immersive Displays
  • Planetary Science and Exploration
  • Piezoelectric Actuators and Control
  • Industrial Vision Systems and Defect Detection
  • Identification and Quantification in Food
  • Advanced MEMS and NEMS Technologies
  • Additive Manufacturing and 3D Printing Technologies
  • Spectroscopy and Chemometric Analyses
  • Aortic Disease and Treatment Approaches
  • Shape Memory Alloy Transformations
  • Astro and Planetary Science
  • Robotic Path Planning Algorithms
  • Teleoperation and Haptic Systems

Purdue University West Lafayette
2023-2025

Jingzhou Central Hospital
2024

Yangtze University
2023-2024

The Ohio State University
2015-2021

Massachusetts Institute of Technology
2018-2021

Vassar College
2021

Corvallis Environmental Center
2020

Harbin Institute of Technology
2012-2015

Jiangxi Normal University
2015

Shenzhen University
2013

This paper details the design and fabrication process of a fully integrated soft humanoid robotic hand with five finger that integrate an embedded shape memory alloy (SMA) actuator piezoelectric transducer (PZT) flexure sensor. Several challenges including precise control SMA actuator, improving power efficiency, reducing actuation current response time have been addressed. First, Ni-Ti strip is pretrained to circular shape. Second, it wrapped Ni-Cr resistance wire coated thermally...

10.1115/1.4029497 article EN Journal of Mechanisms and Robotics 2015-01-07

Cables are complex, high-dimensional, and dynamic objects. Standard approaches to manipulate them often rely on conservative strategies that involve long series of very slow incremental deformations, or various mechanical fixtures such as clamps, pins, rings. We interested in manipulating freely moving cables, real time, with a pair robotic grippers, no added constraints. The main contribution this paper is perception control framework moves direction, uses real-time tactile feedback...

10.1177/02783649211027233 article EN cc-by-nc The International Journal of Robotics Research 2021-08-06

Vision-based tactile sensors have the potential to provide important contact geometry localize objective with visual occlusion. However, it is challenging measure high-resolution 3D for a compact robot finger, simultaneously meet optical and mechanical constraints. In this work, we present GelSight Wedge sensor, which optimized shape fingers, while achieving reconstruction. We evaluate reconstruction under different lighting configurations, extend method from 3 lights 1 or 2 lights....

10.1109/icra48506.2021.9560783 article EN 2021-05-30

In this article, we propose a novel shape memory alloy (SMA) strip-based bending actuator for soft robotic hand. Soft robots have significant advantages of safety, adaptability, and dexterity compared with traditional rigid body robots. However, one challenge is the design modeling effective actuators. This article presents using SMA strips. An analysis model strip are developed to predict output performances provide guidance designers. The experiments conducted verify proposed models. We...

10.1089/soro.2015.0022 article EN Soft Robotics 2016-05-20

Soft robots offer significant advantages in adaptability, safety, and dexterity compared to conventional rigid-body robots. However, it is challenging equip soft with accurate proprioception tactile sensing due their high flexibility elasticity. In this work, we describe the development of a vision-based proprioceptive sensor for called GelFlex, which inspired by previous GelSight techniques. More specifically, develop novel exoskeleton-covered finger embedded cameras deep learning methods...

10.1109/icra40945.2020.9197369 article EN 2020-05-01

Cables are complex, high dimensional, and dynamic objects.Standard approaches to manipulate them often rely on conservative strategies that involve long series of very slow incremental deformations, or various mechanical fixtures such as clamps, pins rings.We interested in manipulating freely moving cables, real time, with a pair robotic grippers, no added constraints.The main contribution this paper is perception control framework moves direction, uses real-time tactile feedback accomplish...

10.15607/rss.2020.xvi.029 article EN 2020-06-30

In this paper, we present a novel wheeled robot that transforms from circled configuration to spoke-like legged configuration. Wheeled mobile robots are able quickly and efficiently move on flat surfaces. However they may sink into terrain with dynamic surface such as snow, sand, dirt, moss, small gravel. The transformable wheel presented in paper is overcome obstacles navigate these dynamics surfaces, yet can still over ground. comprised of five spokes or legs, four which actively driven by...

10.1109/iros.2015.7353966 article EN 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2015-09-01

Continuum space manipulators have wide application prospect in the complex environment with small space. Efficient and accurate static models are very important for continuum manipulators. However, existing of cable-driven manipulators, which based on theories elasticity, often not conducive to efficient computing. In this work, manipulator is equivalent traditional rigid one by pseudorigid-body 3R model. We establish equation manipulator, takes into account effects friction, multi-segment...

10.1109/access.2018.2881261 article EN cc-by-nc-nd IEEE Access 2018-01-01

Reliable robotic grasping, especially with deformable objects such as fruits, remains a challenging task due to underactuated contact interactions gripper, unknown object dynamics and geometries. In this study, we propose Transformer-based grasping framework for rigid grippers that leverage tactile visual information safe grasping. Specifically, the Transformer models learn physical feature embeddings sensor feedback through performing two pre-defined explorative actions (pinching sliding)...

10.1109/tmech.2024.3400789 article EN IEEE/ASME Transactions on Mechatronics 2024-01-01

The poultry industry plays a pivotal role in global agriculture, serving as major source of protein and contributing significantly to economic growth. However, the sector faces challenges associated with labor-intensive tasks that are repetitive physically demanding. Automation has emerged critical solution enhance operational efficiency improve working conditions. Specifically, robot manipulation handling objects is becoming ubiquitous factories. exist precisely identify guide handle pile...

10.20944/preprints202501.1874.v1 preprint EN 2025-01-26

10.1109/lra.2025.3542317 article EN IEEE Robotics and Automation Letters 2025-01-01

The poultry industry plays a pivotal role in global agriculture, with serving as major source of protein and contributing significantly to economic growth. However, the sector faces challenges associated labor-intensive tasks that are repetitive physically demanding. Automation has emerged critical solution enhance operational efficiency improve working conditions. Specifically, robotic manipulation handling objects is becoming ubiquitous factories. exist precisely identify guide robot...

10.3390/agriengineering7030077 article EN cc-by AgriEngineering 2025-03-12

Tactile sensing is pivotal for enhancing robot manipulation abilities by providing crucial feedback localized information. However, existing sensors often lack the necessary resolution and bandwidth required intricate tasks. To address this gap, we introduce VibTac, a novel multi-modal tactile finger designed to offer high-resolution high-bandwidth simultaneously. VibTac seamlessly integrates vision-based vibration-based modes achieve respectively, leveraging streamlined human-inspired...

10.1109/toh.2025.3561049 article EN IEEE Transactions on Haptics 2025-01-01

Tactile sensors are crucial in providing contact geometry information necessary for object manipulation. However, it remains highly nontrivial a tactile sensor to be able perceive distant before In this work, we present an innovative robotic finger, VisTac, which seamlessly combines high-resolution and visual perception single unified device, while adhering essential mechanical constraints, such as human-finger-like wedge-shaped top, vital manipulation tasks. Furthermore, discuss the...

10.1109/jsen.2023.3310918 article EN IEEE Sensors Journal 2023-09-06

In this paper, we present a tunable stiffness robot link for safe human-robot interaction. Stiffness of manipulator determines the injury levels human from an impact between robots and operators, given specific velocity. Compliance includes joint compliance compliance. Variable design viewpoint actuators have been widely studied, while adjustable robotic in application interaction is rare literatures. This paper details via four bar linkages which are actuated by servo motors. A 3D model...

10.1115/detc2016-59523 article EN 2016-08-21

In this paper, we propose a variable width compliant link that is designed for optimal trade-off of safety and control performance inherently safe corobots. Intentionally introducing compliance to mechanical design increases Traditional approaches mostly focus on the joint compliance, while few them study compliance. Here, novel method robotic links with constraint which quantified by head injury criterion (HIC). The are modeled as two-dimensional beams width. Given threshold, i.e., HIC...

10.1115/1.4038530 article EN Journal of Mechanisms and Robotics 2017-11-21

Abstract Variable stiffness robots may provide an effective way of trading-off between safety and speed during physical human–robot interaction. In such a compromise, the impact force reduction capability maximum safe are two key performance measures. To quantitatively study how dynamic parameters as mass, inertia, affect these measures, indices for variable proposed based on ellipsoid in this paper. The consider different directions kinematic configurations large. Combining indices, global...

10.1115/1.4046839 article EN Journal of Mechanisms and Robotics 2020-04-08

In this paper, we study the effect of mechanical compliance on impact force human-robot interactions, more specifically maximum during a collision. Here consider two methods introducing to industrial manipulators: joint and link compliance. To compare their force, designs 2D robot link: rigid with torsion spring at uniform compliant link. The dynamic model is based Hertz contact model. results show that solution could produce larger than if arm mass end mass, given same lateral stiffness all...

10.1109/icra.2017.7989795 article EN 2017-05-01
Coming Soon ...