A robust control of robot manipulators for physical interaction: stability analysis for the interaction with unknown environments

Intelligent Service Robotics - A robust control designed for multiple degrees-of-freedom (DOF) robot manipulators performing complex tasks requiring frequent physical interaction with unknown...     

Research on hydrophobicity of electrospun Fe3O4/PVDF nanofiber membranes under different preparation conditions

Abstract

Preparation condition can affect the structure and the properties of nanofiber membrane. In order to explore suitable conditions to prepare the Fe₃O₄/PVDF nanofiber membrane with good hydrophobicity, the hydrophobicity of Fe₃O₄/PVDF nanofiber membranes obtained by electrospinning was investigated by changing preparation conditions like weight percentage of Fe₃O₄ nanoparticles, blending quality concentration of poly (vinylidene fluoride) (PVDF) and Fe₃O₄ nanoparticles, and positive voltage. And the variations of hydrophobicity of Fe₃O₄/PVDF nanofiber membranes modified by 1H, 1H, 2H, 2H-perfluorodecyl trimethoxysilane were studied. The results show that the hydrophobicity of Fe₃O₄/PVDF nanofiber membranes has changed under different preparation conditions. The contact angles of samples increased after a modification by 1H, 1H, 2H, 2H-perfluorodecyl trimethoxysilane, which indicates that the hydrophobicity of Fe₃O₄/PVDF nanofiber membranes has been enhanced.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

Decorating surface charge of graphite nanoplate using an electrostatic coupling agent for 3-dimensional polymer nanocomposite

Here, we report a facile approach to electrostatically couple the surface charges of graphite nanoplate (GNP) fillers and poly(methyl methacrylate) (PMMA) polymer particles using ethylene maleic anhydride (EMA) copolymer as an electrostatic coupling agent. Our strategy involved switching the intrinsic repulsive electrostatic interactions between the directly exfoliated GNPs fillers and the PMMA particles to attractive electrostatic surface interactions for preparing core(PMMA)-shell (GNP) precursor in order to optimizing 3-dimensionally dispersed polymer nanocomposite. As a result, the electrical conductivity of the composites dramatically increased by a factor of 16.7 in the EMA-coupled GNP/PMMA composites compared with that of the EMA-free GNP/PMMA composites. In addition, the percolation threshold was also notably reduced from 0.32 to 0.159 vol% after electrostatic coupling of the GNPs fillers and PMMA particles. © 2019 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2020 , 137, 48390.