Search

Your search keyword '"Liu Shaopeng"' showing total 688 results
Start Over Author "Liu Shaopeng"
688 results on '"Liu Shaopeng"'

1. Hybrid Robot Learning for Automatic Robot Motion Planning in Manufacturing

Author

Singh, Siddharth, Yu, Tian, Chang, Qing, Karigiannis, John, and Liu, Shaopeng

Subjects
Computer Science - Robotics
Abstract

Industrial robots are widely used in diverse manufacturing environments. Nonetheless, how to enable robots to automatically plan trajectories for changing tasks presents a considerable challenge. Further complexities arise when robots operate within work cells alongside machines, humans, or other robots. This paper introduces a multi-level hybrid robot motion planning method combining a task space Reinforcement Learning-based Learning from Demonstration (RL-LfD) agent and a joint-space based Deep Reinforcement Learning (DRL) based agent. A higher level agent learns to switch between the two agents to enable feasible and smooth motion. The feasibility is computed by incorporating reachability, joint limits, manipulability, and collision risks of the robot in the given environment. Therefore, the derived hybrid motion planning policy generates a feasible trajectory that adheres to task constraints. The effectiveness of the method is validated through sim ulated robotic scenarios and in a real-world setup., Comment: 35 Pages, 11 Figures more...

Published
2025

Catalog

Books, media, physical & digital resources
See catalog results

4. Preparation of Ta/W Composite by CVD

Author

QI Xiaohong, ZHENG Xu, CAI Hongzhong, LIU Shaopeng, HU Changyi, and WEI Yan

Subjects
chemical vapor deposition (CVD), Ta/W composite, volume fraction of W, mechanical properties, Motor vehicles. Aeronautics. Astronautics, TL1-4050
Abstract

The Ta/W composites with 10%W, 13%W and 18%W were prepared by chemical vapor deposition (CVD). The properties of Ta/W composites were investigated by optical microscopy (OM), scanning electron microscopy (SEM ) and tensile test. The results show that it is possible to prepare Ta/W composites with different W volume fractions by CVD, and the actual densities of the composites are more than 99.4% of the theoretical density. Both Ta and W layers have columnar grain structures, and the more close to the interface, the more fine the grains are. The mechanical properties of CVD Ta/W are better than those of CVD Ta or CVD W. After hot treatment(1600 ℃×2 h),the diffused layers of the composites have become more wider and the mechanical properties are increased remarkably, and the tensile strength of the CVD Ta/W composite with 18%W is 660 MPa. more...

Published
2017
Full Text
View/download PDF

20. Progress toward a universal biomedical data translator

Author

Fecho, Karamarie, Thessen, Anne E, Baranzini, Sergio E, Bizon, Chris, Hadlock, Jennifer J, Huang, Sui, Roper, Ryan T, Southall, Noel, Ta, Casey, Watkins, Paul B, Williams, Mark D, Xu, Hao, Byrd, William, Dančík, Vlado, Duby, Marc P, Dumontier, Michel, Glusman, Gustavo, Harris, Nomi L, Hinderer, Eugene W, Hyde, Greg, Johs, Adam, Su, Andrew I, Qin, Guangrong, Zhu, Qian, Dougherty, Jennifer, Huang, Conrad, Magis, Andrew, Smith, Brett, Celebi, Remzi, Chen, Zhehuan, Azevedo, Ricardo De Miranda, Emonet, Vincent, Lee, Jay, Weng, Chunhua, Yilmaz, Arif, Kim, Keum Joo, Santos, Eugene, Tonstad, Lucas, Veenhuis, Luke, Yakaboski, Chase, Acevedo, Liliana, Carrell, Steven, Deutsch, Eric, Glen, Amy, Hoffman, Andrew, Koslicki, David, Kvarfordt, Lindsey, Liu, Zheng, Liu, Shaopeng, Ma, Chunyu, Mendoza, Luis, Muluka, Arun Teja, Womack, Finn, Wood, Erica, Roach, Jared, Goel, Prateek, Weber, Rosina, Williams, Andrew, Gormley, Joseph, Zisk, Tom, Hanspers, Kristina, Hoatlin, Maureen, Pico, Alexander, Riutta, Anders, Callaghan, Jackson, Xu, Colleen, Ahalt, Stanley C, Balhoff, Jim, Edwards, Stephen, Haaland, Perry, Knowles, Michael, Krishnamurthy, Ashok, Mandal, Meisha, Peden, David B, Pfaff, Emily, Schurman, Shepherd, Shrivastava, Shalki, Yi, Hong, Reilly, Jason, Kanwar, Richa, Cox, Steven, Vaidya, Gaurav, Wang, Max, Alkanaq, Ahmed, Costanzo, Maria, Koesterer, Ryan, Flannick, Jason, Burtt, Noel, Kluge, Alexandria, Rubin, Irit, Strasser, Michael Michi, Chung, Lawrence, Kang, Jimin, Mantilla, Michelle, Muller, Sandrine, Persaud, Bria, Wei, Qi, Baumgartner, Andrew, Dai, Cheng, and Duvvuri, Venkata more...

Subjects
Pharmacology and Pharmaceutical Sciences, Biomedical and Clinical Sciences, Cardiovascular Medicine and Haematology, Biomedical Data Translator Consortium, Cardiorespiratory Medicine and Haematology, Oncology and Carcinogenesis, Other Medical and Health Sciences, General Clinical Medicine, Cardiovascular medicine and haematology, Pharmacology and pharmaceutical sciences
Abstract

Clinical, biomedical, and translational science has reached an inflection point in the breadth and diversity of available data and the potential impact of such data to improve human health and well-being. However, the data are often siloed, disorganized, and not broadly accessible due to discipline-specific differences in terminology and representation. To address these challenges, the Biomedical Data Translator Consortium has developed and tested a pilot knowledge graph-based "Translator" system capable of integrating existing biomedical data sets and "translating" those data into insights intended to augment human reasoning and accelerate translational science. Having demonstrated feasibility of the Translator system, the Translator program has since moved into development, and the Translator Consortium has made significant progress in the research, design, and implementation of an operational system. Herein, we describe the current system's architecture, performance, and quality of results. We apply Translator to several real-world use cases developed in collaboration with subject-matter experts. Finally, we discuss the scientific and technical features of Translator and compare those features to other state-of-the-art, biomedical graph-based question-answering systems. more...

Published
2022

27. Feature Space Augmentation for Long-Tailed Data

Author

Chu, Peng, Bian, Xiao, Liu, Shaopeng, and Ling, Haibin

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than sufficient data. However, a model to represent the dataset is usually expected to have reasonably homogeneous performances across classes. Introducing class-balanced loss and advanced methods on data re-sampling and augmentation are among the best practices to alleviate the data imbalance problem. However, the other part of the problem about the under-represented classes will have to rely on additional knowledge to recover the missing information. In this work, we present a novel approach to address the long-tailed problem by augmenting the under-represented classes in the feature space with the features learned from the classes with ample samples. In particular, we decompose the features of each class into a class-generic component and a class-specific component using class activation maps. Novel samples of under-represented classes are then generated on the fly during training stages by fusing the class-specific features from the under-represented classes with the class-generic features from confusing classes. Our results on different datasets such as iNaturalist, ImageNet-LT, Places-LT and a long-tailed version of CIFAR have shown the state of the art performances., Comment: To be appeared in ECCV 2020 more...

Published
2020

32. KGESS - A Knowledge Graph Embedding Method Based on Semantics and Structure

Author

Chen, Xunhan, Ma, Zhiyong, Xiao, Zhenghong, Xia, Qi, Liu, Shaopeng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Memmi, Gerard, editor, Yang, Baijian, editor, Kong, Linghe, editor, Zhang, Tianwei, editor, and Qiu, Meikang, editor more...

Published
2022
Full Text
View/download PDF

41. A Class Imbalance Monitoring Model for Fetal Heart Contractions Based on Gradient Boosting Decision Tree Ensemble Learning

Author

Qin, Chen, Liu, Shaopeng, Lin, Shengxiang, Li, Guangzhe, Hong, Jiaming, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Tan, Ying, editor, Shi, Yuhui, editor, Zomaya, Albert, editor, Yan, Hongyang, editor, and Cai, Jun, editor more...

Published
2021
Full Text
View/download PDF

42. A Multiobjective Memetic Algorithm for Multiobjective Unconstrained Binary Quadratic Programming Problem

Author

Zhou, Ying, Kong, Lingjing, Yan, Lijun, Liu, Shaopeng, Hong, Jiaming, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Tan, Ying, editor, and Shi, Yuhui, editor more...

Published
2021
Full Text
View/download PDF

43. High-precision realization for sensing charged particles based on optomechanically induced two-color second-order sidebands.

Author

Wang, Junfeng, Xue, Yafeng, Liu, Shaopeng, Li, Ying, and Liu, Bo

Subjects
NONLINEAR oscillators, PARTICLE beams, ABSORPTION spectra, SENSES
Abstract

We propose an effective scheme to sense charged particles by employing two-color second-order sidebands (TSSs) in a hybrid optomechanical system. This is realized in an optomechanical cavity with a double-oscillator structure, where the Coulomb force acting on two charged oscillators participates in nonlinear optomechanical interaction. With the aid of mechanical mode splitting induced by the Coulomb force, we report that the TSS spectrum can be generated and enhanced when the strong absorption in the transmission spectrum allows the TSS generated pathways to be readily accessed. More importantly, after seeking two correlations between the TSS spectra and the charged particles deposited on the oscillator, we design a dual-parameter sensor to measure the mass and the charge of the external particles simultaneously. Through evaluating the influence of the thermomechanical noise on the optomechanical sensing device, the resolution for detecting the mass and the charge of the measured particles can be identified as δ m ≈ 1.7 × 10 − 18 g and δ Q ≈ 1.6 × 10 − 18 C , respectively. [ABSTRACT FROM AUTHOR] more...

Published
2023
Full Text
View/download PDF