A5107954261- Robot Manipulation and Learning
- Robotic Mechanisms and Dynamics
- Soft Robotics and Applications
- Transportation Planning and Optimization
- Cell Image Analysis Techniques
- Motor Control and Adaptation
- Hallucinations in medical conditions
- Advanced Measurement and Metrology Techniques
- 3D Surveying and Cultural Heritage
- Modular Robots and Swarm Intelligence
- Image Processing Techniques and Applications
- Optical measurement and interference techniques
- Advanced machining processes and optimization
- Advanced Control Systems Optimization
- Robotic Locomotion and Control
- Interactive and Immersive Displays
- Robotics and Sensor-Based Localization
- Network Time Synchronization Technologies
- Electric and Hybrid Vehicle Technologies
- Railway Systems and Energy Efficiency
- Industrial Vision Systems and Defect Detection
- Advanced MEMS and NEMS Technologies
- Music and Audio Processing
- Vehicle Dynamics and Control Systems
- Real-time simulation and control systems
China Southern Power Grid (China)
2024
Tsinghua University
2009-2024
Jiangxi University of Science and Technology
2024
North China Electric Power University
2024
Beijing University of Chemical Technology
2020
University Town of Shenzhen
2019
University of Hong Kong
2019
Nanyang Technological University
2015
Manipulating deformable linear objects (DLOs) to achieve desired shapes in constrained environments with obstacles is a meaningful but challenging task. Global planning necessary for such highly-constrained task; however, accurate models of DLOs required by planners are difficult obtain owing their nature, and the inevitable modeling errors significantly affect results, probably resulting task failure if robot simply executes planned path an open-loop manner. In this paper, we propose...
Constrained environments, compared with open spaces without other objects, are more common in practical applications of manipulating deformable linear objects (DLOs) by robots, where movements both DLOs and robot manipulators should be constrained unintended collision avoided. Such a task is high-dimensional highly owing to the DLOs, dual-arm robots high degrees freedom, 3-D complex which render global planning extremely challenging. Furthermore, accurate DLO models needed often unavailable...
Large demand for robotics and automation has been reflected in the sanding works, as current manual operations are labor-intensive, without consistent quality, also subject to safety health issues. While several machines have developed automate one or two steps autonomous capability of existing solutions is relatively low, human assistance supervision still heavily required calibration target objects planning robot motion tasks. This paper presents development an robot, which able perform...
Vehicle controller unit (VCU) plays an important role in fuel cell/battery hybrid vehicles and there is a need to investigate the influence of embedded algorithm on vehicle performance. An effective way for such investigation via hardware-in-the-loop (HIL) simulation. This paper describes HIL simulation system that developed this purpose. overview provided, followed by descriptions models dynamics, electric motor, cell, battery etc.. The control contains two parts, driver command explanation...
Generative image reconstruction algorithms such as measurement conditioned diffusion models are increasingly popular in the field of medical imaging. These powerful can transform low signal-to-noise ratio (SNR) inputs into outputs with appearance high SNR. However, have a new type error called hallucinations. In imaging, these hallucinations may not be obvious to Radiologist but could cause diagnostic errors. Generally, hallucination refers estimation object structure caused by machine...
Re-grasp manipulation leverages on ergonomic tools to assist humans in accomplishing diverse tasks. In certain scenarios, often employ external forces effortlessly and precisely re-grasp like a hammer. Previous development controllers for in-grasp sliding motion using passive dynamic actions (e.g.,gravity) relies apprehension of finger-object contact information, requires customized design individual objects with varied geometry weight distribution. It limits their adaptability objects. this...
As one of few effective perception measures in the micro world, vision provides important feedback about position micro-objects; Different from visual at macro scale, world is facing its own challenges. For example, multiple micro-objects often sway medium or overlap different depths; The environment dynamic sense that some objects may enter leave field view during manipulation. This paper reports development a deep network for micromanipulation, which able to detect and output real-time...