A5000956717- Robot Manipulation and Learning
- Soft Robotics and Applications
- Robotic Mechanisms and Dynamics
- Robotics and Sensor-Based Localization
- Nanomaterials for catalytic reactions
- Graphene and Nanomaterials Applications
- Adsorption and biosorption for pollutant removal
- Advanced Manufacturing and Logistics Optimization
- Manufacturing Process and Optimization
- Microbial Metabolic Engineering and Bioproduction
- Graphene research and applications
- Carbon and Quantum Dots Applications
- Microplastics and Plastic Pollution
- Environmental remediation with nanomaterials
- Modular Robots and Swarm Intelligence
- Membrane Separation Technologies
- Robotic Path Planning Algorithms
- Hand Gesture Recognition Systems
- Lipid metabolism and biosynthesis
- Enzyme Catalysis and Immobilization
- Nanopore and Nanochannel Transport Studies
Harbin Institute of Technology
2019-2020
Zhejiang Medicine (China)
2020
Hunan University
2016-2017
In this study, diethylenetriaminepentaacetic acid (DTPA)-modified magnetic graphene oxide (MGO) was synthesized for removal of Cu(II), Pb(II), and Cd(II) ions from acidic aqueous solutions. The prepared DTPA/MGO composites were characterized by scanning electron microscopy, X-ray diffraction, Fourier transform infrared photoelectron spectroscopies, zeta potential. results showed that DTPA successfully functionalized MGO. Adsorption experiments indicated exhibited excellent adsorption...
This paper presents an efficient neural network model to generate robotic grasps with high resolution images. The proposed uses fully convolution for each pixel using 400 × RGB-D It first down-sample the images get features and then up-sample those original size of input as well combines local global from different feature maps. Compared other regression or classification methods detecting grasps, our method looks more like segmentation which solves problem through pixel-wise ways. We use...
In logistics warehouse sorting, rubbish classification, and household services, scenarios exist in which rigid soft objects are randomly piled together. such situations, two major challenges arise robotic picking tasks: the first is to distinguish from objects, second grasp one object of each type at a time. this study, we propose novel methodology for grasping mixed with towels. The proposed approach based on detection method that can identify placed different directions using rotational...
In industry assembly lines, parts feeding machines are widely employed as the prologue of whole procedure. They play role sorting randomly placed in bins to state with specified pose. With help machines, subsequent processes by robot arm can always start from same condition. Thus it is expected that function parting machine and robotic be integrated one arm. This scheme provide great flexibility also contribute reduce cost. The difficulties involved this lie fact part phase, pose after...
Picking clothing has always been a great challenge in laundry or textile industry automation, especially when some clothes are of the same colors, material and entangled with each other. In order to solve problem, we present grasp pose determination method pick towels placed basket on table. our method, it is not needed segment into independent items target necessarily distinguishable color. The proposed algorithm firstly segments point clouds several convex wrinkles, then selects...
In this paper, we propose a object detection method expressed as rotated bounding box to solve grasping challenge in the scenes where rigid objects and soft are mixed together. Compared with traditional methods, can output angle information of thus guarantee that within each box, there is single instance. This technology especially useful case pile different orientations. our method, when uncategorized specific geometry shapes (rectangle or cylinder) detected, program will conclude some...
This paper presents an efficient neural network model to generate robotic grasps with high resolution images. The proposed uses fully convolution for each pixel using 400 $\times$ RGB-D It first down-sample the images get features and then up-sample those original size of input as well combines local global from different feature maps. Compared other regression or classification methods detecting grasps, our method looks more like segmentation which solves problem through pixel-wise ways. We...
This paper presents a vision based robotic system to handle the picking problem involved in automatic express package dispatching. By utilizing two RealSense RGB-D cameras and one UR10 industrial robot, dispatching task which is usually done by human can be completed automatically. In order determine grasp point for overlapped deformable objects, we improved sampling algorithm proposed group Berkeley directly generate candidate from depth images. For purpose of recognition, deep network...
This paper presents a vision based robotic system to handle the picking problem involved in automatic express package dispatching. By utilizing two RealSense RGB-D cameras and one UR10 industrial robot, dispatching task which is usually done by human can be completed automatically. In order determine grasp point for overlapped deformable objects, we improved sampling algorithm proposed group Berkeley directly generate candidate from depth images. For purpose of recognition, deep network...
In industry assembly lines, parts feeding machines are widely employed as the prologue of whole procedure. They play role sorting randomly placed in bins to state with specified pose. With help machines, subsequent processes by robot arm can always start from same condition. Thus it is expected that function parting machine and robotic be integrated one arm. This scheme provide great flexibility also contribute reduce cost. The difficulties involved this lie fact part phase, pose after...