A5101946797- Soft Robotics and Applications
- Robot Manipulation and Learning
- Structural Health Monitoring Techniques
- Probabilistic and Robust Engineering Design
- Bladed Disk Vibration Dynamics
- Robotic Path Planning Algorithms
- Railway Engineering and Dynamics
- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Micro and Nano Robotics
- Maritime Navigation and Safety
- Enhanced Oil Recovery Techniques
- Face and Expression Recognition
- Image Processing Techniques and Applications
- Dyeing and Modifying Textile Fibers
- Acoustic Wave Phenomena Research
- Music Technology and Sound Studies
- Consumer Perception and Purchasing Behavior
- Advanced Data Compression Techniques
- Software Engineering Research
- Reinforcement Learning in Robotics
- Non-Destructive Testing Techniques
- Airway Management and Intubation Techniques
- Medical Imaging and Analysis
- Surgical Simulation and Training
Tsinghua University
2011-2024
Northeastern University
2022-2024
Tarim University
2024
Panzhihua University
2023
Chinese Academy of Sciences
2021-2023
University of Chinese Academy of Sciences
2023
Shanghai Institute of Materia Medica
2023
Renmin University of China
2022
Institute of Automation
2021
Australian National University
2021
Mechanism design has long been a cornerstone of economic theory, with traditional approaches relying on mathematical derivations. Recently, automated approaches, including differentiable economics neural networks, have emerged for designing payments and allocations. While both analytical methods advanced the field, they each face significant weaknesses: derivations are not often struggle to scale complex problems, while especially neural-network-based suffer from limited interpretability. To...
The trajectory planning algorithm of underwater vehicle near-bottom cruise is important to scientific investigation, industrial inspection, and military affairs. An autonomous (AUV) often faces the problems complex environment large area in a real environment, some robots must hide themselves during cruise. However, best our knowledge, few studies have focused on algorithms for AUVs with multiple constraints large-scale maps. currently used are not effective at solving length-constraint...
Safe human-robot interaction and excellent motion flexibility ensure a wide range of potential applications for soft robots in industry medicine. Although many efforts have been made to empower with variable stiffness, solutions miniaturization, wide-range, rapid-response stiffness yet be realized. To maintain the combination operation stability, this work manipulator diameter 10.7 mm based on low melting point alloy (LMPA) solution is proposed. Inspired by reinforced concrete structures,...
Soft robots have garnered considerable interest in recent years terms of structure and functionality, while commercially viable pressure supply systems with various modes for soft remain slow to progress. Hence, this work, a palm-sized multi-mode system based on peristaltic pump is proposed the first time, precise pneumatic control achieved model reference adaptive (MRAC) method dynamics. Further performance evaluation demonstrates that our can deliver positive (mean error < 0.48 kPa 0...
Abstract Compared to rigid-structure robots, soft robots possess higher degrees of freedom and stronger environmental adaptability, which has aroused increasing attention in the robotic field. Among them, pneumatic have excellent performances various practical applications. However, nonlinearity instability pressure response actuators caused by lateral expansion come a great challenge. To address this problem, we proposed embed spring constraint layer around each single air chamber....
Impulse response functions (IRFs) and frequency (FRFs) are bases for modal parameter identification of single-input, single-output (SISO) multiple-input, multiple-out (MIMO) systems, the two can be transformed from each other using fast Fourier transform inverse transform. An efficient iterative algorithm is developed in this work to directly accurately calculate IRFs SISO MIMO systems time domain relatively short input output data series. The avoid time-consuming inversion a large matrix...
Modular Reinforcement Learning (RL) decentralizes the control of multi-joint robots by learning policies for each actuator. Previous work on modular RL has proven its ability to morphologically different agents with a shared actuator policy. However, increase in Degree Freedom (DoF) robots, training morphology-generalizable controller becomes exponentially difficult. Motivated way human central nervous system controls numerous muscles, we propose Synergy-Oriented LeARning (SOLAR) framework...
3D reconstruction of insects from photographs is a challenging task as it requires to tackle several problems such strong out-of-focus areas in macro-photography, thin structures (insect legs and hairs), flat-colored surfaces (insects shells), non-Lambertian (shells specularities) even translucent (wings). In this work, we first present new lens-based image registration technique for accurate multi-focus stacking suitable purposes while other methods create in-focus images viewing purpose...
Payment Channel Network (PCN) is proposed as a promising layer-two solution to tackle the scalability problem of current blockchain systems, which allows two transacting parties perform off-chain transactions through their established payment channel. For who are not directly connected, PCN them route transaction some intermediate nodes with sufficient balance. Designing an efficient routing protocol one most important and challenging problems in improving performance PCN. To this challenge,...
There is about 1% vanadium residue in the roasting roasted-acid tailings after industrial extraction. How to properly treat vanadium-containing has become a hot topic environmental field. In this study, novel extraction process based on synergistic treatment of ultrasonic and H2O2 enhanced acid leaching was developed for highly toxic valuable calcification tailings. The effect different experimental conditions rate explored. results demonstrated that reached 72% through treatment. contrast,...