检索结果-内蒙古大学图书馆

An Integrated Neural Unmanned System for Multi-Domain Perception and Decision-Making

学校读者我要写书评

暂无评论

An Integrated Neural Unmanned System for Multi-Domain Percep...

IEEE International Conference on Robotics and Biomimetics

作者： Qiming Liu Neng Xu Jinpeng Zhang Hesheng Wang Department of Automation Shanghai Jiao Tong University Shanghai China SJTU Paris Elite Institute of Technology Shanghai Jiao Tong University Shanghai China Second Academy of China Aerospace Science and Industry Corporation (CASIC) Beijing China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665481106

Most recent intelligent systems study the perception or policy modules independently but ignore the inter-connection between them, which results in low information efficiency and high network redundancy, in the end, leads to the incomplete utilization of network potential and poor system-level end-to-end intelligence. This paper proposes an integrated end-to-end network that adapts to multi-domain inputs and multi-function outputs. “Integration” is defined in this paper in mainly three aspects: network structure level, optimization level, and functional level. The integrated network architecture is capable of fusing multiple raw sensory inputs and outputting multiple perceptions and decisions simultaneously. We first implement the integrated system in a virtual simulation environ-ment and investigate the domain transformation methods to real world. Comprehensive experiment results in both virtual and real environments show that our proposed system can behave normally under exploration, target-driven navigation and target shooting tasks.

关键词： Training Point cloud compression Target tracking Navigation Robot kinematics Redundancy Robot sensing systems

controllability of giant connected components in a directed network

学校读者我要写书评

暂无评论

Physical Review E 2017年第4期95卷 042318-042318页

作者： Xueming Liu Linqiang Pan H. Eugene Stanley Jianxi Gao Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Wuhan 430074 Hubei China Center for Polymer Studies and Department of Physics Boston University Boston Massachusetts 02215 USA School of Electric and Information Engineering Zhengzhou University of Light Industry Zhengzhou 450002 Henan China Center for Complex Network Research and Department of Physics Northeastern University Boston Massachusetts 02115 USA

When controlling a complex networked system it is not feasible to control the full network because many networks, including biological, technological, and social systems, are massive in size and complexity. But neither is it necessary to control the full network. In complex networks, the giant connected components provide the essential information about the entire system. How to control these giant connected components of a network remains an open question. We derive the mathematical expression of the degree distributions for four types of giant connected components and develop an analytic tool for studying the controllability of these giant connected components. We find that for both Erdős-Rényi (ER) networks and scale-free (SF) networks with p fraction of remaining nodes, the minimum driver node density to control the giant component first increases and then decreases as p increases from zero to one, showing a peak at a critical point p=pm. We find that, for ER networks, the peak value of the driver node density remains the same regardless of its average degree 〈k〉 and that it is determined by pm〈k〉. In addition, we find that for SF networks the minimum driver node densities needed to control the giant components of networks decrease as the degree distribution exponents increase. Comparing the controllability of the giant components of ER networks and SF networks, we find that when the fraction of remaining nodes p is low, the giant in-connected, out-connected, and strong-connected components in ER networks have lower controllability than those in SF networks.

关键词： Network structure

Learning of long-horizon sparse-reward robotic manipulator tasks with base controllers

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Guangming Xin, Minjian Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Engineering University of California San Diego La Jolla CA92093 United States Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporates the existing base controllers into stages of exploration, value learning, and policy update. Furthermore, we present a straightforward way of synthesizing different base controllers to integrate their strengths. Through experiments ranging from stacking blocks to cups, it is demonstrated that the learned state-based or image-based policies steadily outperform base controllers. Compared to previous works of learning from demonstrations, our method improves sample efficiency by orders of magnitude and improves the performance. Overall, our method bears the potential of leveraging existing industrial robot manipulation systems to build more flexible and intelligent controllers. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Guangming Zhong, Jiquan Zhao, Shijie Wu, Wenhua Liu, Zhe Wang, Hesheng Department of Automation Institute of Medical Robotics Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Engineering Mechanics Shanghai Jiao Tong University Shanghai200240 China Department of Computer Science and Technology University of Cambridge CambridgeCB2 1TN United Kingdom

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Robots

A Single-Cell Clustering Algorithm Based on Structure Perturbation Non-Negative Matrix Factorization

学校读者我要写书评

暂无评论

A Single-Cell Clustering Algorithm Based on Structure Pertur...

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Hanjing Wang, Meineng Zhang, Luping Huang, Yu-An Li, Yangyuan Huang, Yabing Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Hubei Wuhan430074 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Yichun University School of Mathematics and Computer Science Yichun336000 China East China University of Technology School of Information Engineering Nanchang330013 China Northwestern Polytechnical University School of Computer Science Xi'an710129 China Renmin Hospital Wuhan University Department of Pathology Wuhan430060 China

ISBN: (纸本)9798350386226

The advent of single-cell RNA sequencing (scRNA-seq) has facilitated the acquisition of high-resolution data regarding cell heterogeneity across various tissues. A fundamental and critical step in the analysis of scRNA-seq data is cell type identification. An appropriate graph construction strategy can reflect the topological structure between cells and allows for detailed exploration of the relationships between cells and genes. Given the sparsity of scRNA-seq data and the pronounced noise generated by shallow sequencing, choosing an appropriate graph construction strategy has become a significant challenge. In this paper, we propose a single-cell clustering method, named Sc-PNNMF, based on structural perturbation of nonnegative matrix factorization. Sc-PNNMF employs a structural perturbation algorithm to optimize the gene expression matrix. The optimized matrix guides the matrix factorization process, effectively overcoming the impact of data sparsity and significant noise in gene expression data on the graph construction strategy. We compared the clustering abilities of Sc-PNNMF with five other methods on ten real datasets. © 2024 IEEE.

关键词： Non-negative matrix factorization

Differential Private Discrete Noise Adding Mechanism: Conditions, Properties and Optimization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qin, Shuying He, Jianping Fang, Chongrong Lam, James The Dept. of Automation Shanghai Jiao Tong University The Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China The Dept. of Mechanical Engineering The University of Hong Kong Pokfulam Road Hong Kong

Differential privacy is a standard framework to quantify the privacy loss in the data anonymization process. To preserve differential privacy, a random noise adding mechanism is widely adopted, where the trade-off between data privacy level and data utility is of great concern. The privacy and utility properties for the continuous noise adding mechanism have been well studied. However, the related works are insufficient for the discrete random mechanism on discretely distributed data, e.g., traffic data, health records. This paper focuses on the discrete random noise adding mechanisms. We study the basic differential privacy conditions and properties for the general discrete random mechanisms, as well as the trade-off between data privacy and data utility. Specifically, we derive a sufficient and necessary condition for discrete ∊-differential privacy and a sufficient condition for discrete (∊, δ)-differential privacy, with the numerical estimation of differential privacy parameters. These conditions can be applied to analyze the differential privacy properties for the discrete noise adding mechanisms with various kinds of noises. Then, with the differential privacy guarantees, we propose an optimal discrete ∊-differential private noise adding mechanism under the utility-maximization framework, where the utility is characterized by the similarity of the statistical properties between the mechanism's input and output. For this setup, we find that the class of the discrete noise probability distributions in the optimal mechanism is Staircase-shaped. Copyright © 2022, The Authors. All rights reserved.

关键词： Probability distributions

Industrial Scene Text Detection with Refined Feature-attentive Network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Guan, Tongkun Gu, Chaochen Lu, Changsheng Tu, Jingzheng Feng, Qi Wu, Kaijie Guan, Xinping The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China The College of Engineering and Computer Science The Australian National University CanberraACT2600 Australia

Detecting the marking characters of industrial metal parts remains challenging due to low visual contrast, uneven illumination, corroded surfaces, and cluttered background of metal part images. Affected by these factors, bounding boxes generated by most existing methods could not locate low-contrast text areas very well. In this paper, we propose a refined feature-attentive network (RFN) to solve the inaccurate localization problem. Specifically, we first design a parallel feature integration mechanism to construct an adaptive feature representation from multi-resolution features, which enhances the perception of multi-scale texts at each scale-specific level to generate a high-quality attention map. Then, an attentive proposal refinement module is developed by the attention map to rectify the location deviation of candidate boxes. Besides, a re-scoring mechanism is designed to select text boxes with the best rectified location. To promote the research towards industrial scene text detection, we contribute two industrial scene text datasets, including a total of 102156 images and 1948809 text instances with various character structures and metal parts. Extensive experiments on our dataset and four public datasets demonstrate that our proposed method achieves the state-of-the-art performance. Both code and dataset are available at: https://***/TongkunGuan/RFN. © 2021, CC BY.

关键词： Character recognition

Differentiator-Based Adaptive H∞ Tracking control of Fully Actuated Systems

学校读者我要写书评

暂无评论

Differentiator-Based Adaptive H∞ Tracking Control of Fully ...

Fully Actuated System Theory and Applications (CFASTA), Conference on

作者： Yuxin Feng Zhiqiang Li Yang Liu Zhaoshui He Hongyi Li School of Automation and Guangdong Provincial Key Laboratory of Intelligent Decision and Cooperative Control Guangdong University of Technology Guangzhou China School of Automation and Electronics Engineering Qingdao University of Science and Technology Qingdao China School of Automation Guangdong University of Technology Guangzhou China Key Laboratory for IoT Intelligent Information Processing and System Integration of Ministry of Education Guangzhou China

ISBN: (数字)9798350373691

ISBN: (纸本)9798350373707

This article addresses an adaptive tracking control problem for uncertain high-order fully actuated (HOFA) systems with unknown parameters and disturbances. Under the framework of backstepping, the unknown parameter is estimated and the external disturbance is handled by using adaptive control and H ∞ technique, respectively. Moreover, the Levant differentiator is employed to reduce the computation burden. Additionally, the boundedness of signals in the closed-loop system is proven using the Lyapunov theory. Finally, the effectiveness of the proposed scheme is validated through the simulation study.

关键词： Backstepping Manipulators Stability analysis Closed loop systems Adaptive control Lyapunov methods

Multi-Party dual learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gong, Maoguo Gao, Yuan Xie, Yu Qin, A.K. Pan, Ke Ong, Yew-Soon The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Xi'an Shaanxi Province710071 China The Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Shanxi University Taiyuan030006 China The Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore

The performance of machine learning algorithms heavily relies on the availability of a large amount of training data. However, in reality, data usually reside in distributed parties such as different institutions and may not be directly gathered and integrated due to various data policy constraints. As a result, some parties may suffer from insufficient data available for training machine learning models. In this paper, we propose a multi-party dual learning (MPDL) framework to alleviate the problem of limited data with poor quality in an isolated party. Since the knowledge sharing processes for multiple parties always emerge in dual forms, we show that dual learning is naturally suitable to handle the challenge of missing data, and explicitly exploits the probabilistic correlation and structural relationship between dual tasks to regularize the training process. We introduce a feature-oriented differential privacy with mathematical proof, in order to avoid possible privacy leakage of raw features in the dual inference process. The approach requires minimal modifications to the existing multi-party learning structure, and each party can build flexible and powerful models separately, whose accuracy is no less than non-distributed self-learning approaches. The MPDL framework achieves significant improvement compared with state-of-the-art multi-party learning methods, as we demonstrated through simulations on real-world datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning