检索结果-内蒙古大学图书馆

Attacking End-to-End Visual Navigation Model: How Weak Existing Learning-Based Approaches Can Be?

学校读者我要写书评

暂无评论

Attacking End-to-End Visual Navigation Model: How Weak Exist...

IEEE International Conference on Robotics and Biomimetics

作者： Hongye Wang Kefan Jin Hesheng Wang Shanghai Jiao Tong University China MOE Key Laboratory of Marine Intelligent Equipment and System State Key Laboratory of Ocean Engineering Shanghai Jiao Tong University China 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)9781665405362

Learning-based self-driving techniques and vehicle navigation approaches are the most hot topics in recent years. However, existing approaches typically assume the attack-free sensor data, the safety issue under large disturbance or external attack have not been well-solved. In this article, we build a simple FGSM-based attack method designed by minimizing the maximum value of the extracted visual features in order to greatly decrease the performance of the popular learning model for vehicle navigation and even make it totally fail. The proposed min-max operation based feature space attack method solves the problems of branch activation uncertainties and the lack of labels. Furthermore, we also provide a general adversarial training framework which can be used to overcome the proposed feature space attack. Simulational experiments in CARLA platform demonstrate the effectiveness and practical applicability of our attacking approach and defence strategy.

关键词： Training Space vehicles Visualization Uncertainty Navigation Feature extraction Robustness

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

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

Privacy-Preserving Brain-Computer Interfaces: A Systematic Review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xia, Kun Duch, Wlodzislaw Sun, Yu Xu, Kedi Fang, Weili Luo, Hanbin Zhang, Yi Sang, Dong Xu, Xiaodong Wang, Fei-Yue Wu, Dongrui The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China The Department of Informatics School of Physics Astronomy and Informatics Neurocognitive Laboratory Center for Modern Interdisciplinary Technologies Nicolaus Copernicus University Torun Poland The Ministry of Education Key Laboratory for Biomedical Engineering Zhejiang University Hangzhou China The Zhejiang University School of Medicine National Clinical Research Center for Child Health Hangzhou China Department of Biomedical Engineering Zhejiang University Hangzhou China The School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China The College of Public Administration Huazhong University of Science and Technology Wuhan430074 China The NetsUnion Clearing Corporation Beijing100045 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100049 China

A brain-computer interface (BCI) establishes a direct communication pathway between the human brain and a computer. It has been widely used in medical diagnosis, rehabilitation, education, entertainment, etc. Most research so far focuses on making BCIs more accurate and reliable, but much less attention has been paid to their privacy. Developing a commercial BCI system usually requires close collaborations among multiple organizations, e.g., hospitals, universities, and/or companies. Input data in BCIs, e.g., electroencephalogram (EEG), contain rich privacy information, and the developed machine learning model is usually proprietary. Data and model transmission among different parties may incur significant privacy threats, and hence privacy protection in BCIs must be considered. Unfortunately, there does not exist any contemporary and comprehensive review on privacy-preserving BCIs. This paper fills this gap, by describing potential privacy threats and protection strategies in BCIs. It also points out several challenges and future research directions in developing privacy-preserving BCIs. © 2024, CC BY.

关键词： Differential privacy

Optimizing Neural Network image Classification with Fractional Order Gradient Methods

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhao, Haiming Chen, Jiejie Jiang, Ping Zeng, Zhigang Fan, Rui Yang, Honggang School of Computer and Information Engineering Hubei Normal University Huangshi435000 China School of Automation Wuhan University of Technology Wuhan430000 China School of Computer Hubei PolyTechnic University Huangshi435000 China Faculty of Artificial Intelligence Education Central China Normal University Wuhan430000 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430000 China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430000 China

As deep learning technology increasingly permeates various fields, the significance of optimization algorithms in neural network training has become more prominent. Typically, the training of deep learning networks relies on gradient descent optimizers based on calculus computations. Traditional integer-order calculus optimizers often fall short when dealing with complex and subtle data. To overcome these limitations, we innovatively utilized the Grünwald-Letnikov and Caputo definitions of fractional calculus to develop two new optimization algorithms: Fractional Order Adagrad (FAdagrad) and Fractional Order Adam (FAdam). These algorithms have been proven to converge to extremal points.A key advantage of our methods is their capability in handling complex, high-dimensional tasks, such as artistic painting image classification, where they exhibit exceptional performance in recognizing and processing subtle differences. The robustness and adaptability of these algorithms were further validated through experiments on the CIFAR-100 dataset. The results demonstrate the efficacy of fractional order optimizers in enhancing training efficiency and accuracy. © 2023, The Authors. All rights reserved.

关键词： image classification

Construction of Minecraft Virtual Reality Scene Based on Voxel Point Cloud 8th

学校读者我要写书评

暂无评论

Construction of Minecraft Virtual Reality Scene Based on Vox...

8th International Conference on Cognitive Systems and Information processing, ICCSIP 2023

作者： Ji, Nuocheng Zhuang, Hanyang Yang, Ming The University of Michigan – Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai200240 China Global Institute of Future Technology Shanghai Jiao Tong University Shanghai200240 China Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9789819980208

Virtual Reality is an important development direction in recent years. Minecraft, a popular sandbox game, has a great potential to become a virtual reality platform for building immersive environments. Traditional methods of building virtual reality scenes rely heavily on massive human labors and require high levels of proficiency. To address these limitations, we propose an automatic, voxelated 3D modeling method with foreground and background environment segmented that can reduce modeling costs and achieve effective application in Minecraft virtual reality scenes such as virtual campuses. The proposed method leverages the use of point cloud reconstruction using a voxelization approach. A pipeline of converting point cloud to Minecraft scene is developed. Through preprocessing, segmenting, coloring, and exporting, a Minecraft virtual reality scene can be automatically generated based on voxel point cloud. Due to the noise in point cloud may cause defect during voxelization, a denoising and smoothing method using slice scanning and voxel connectivity segmentation has been implemented. It can generate building structures with clear outlines and uniform colors. And the entire process requires low computational complexity and achieves fast generation. We conducted experiments based on this method in indoor scenes, outdoor building landmarks, and complex underground scenes, and obtained results with clear structures and smooth surfaces, saving a lot of time for subsequent detailed modeling. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： 3D modeling

Giant-cavity-based quantum sensors with enhanced performance

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhu, Y.T. Wu, R.B. Peng, Z.H. Xue, Shibei Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Center for intelligent and networked systems Department of Automation Tsinghua University Beijing100084 China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Key Laboratory for Matter Microstructure and Function of Hunan Province Department of Physics Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha410081 China

Recent progresses have revealed that quantum systems with multiple position-dependent couplings, e.g., giant atoms, can exhibit some unconventional phenomena, such as non-exponential decay etc. However, their potential applications are still open questions. In this paper, we propose a giant-cavity-based quantum sensor for the first time, whose performance can be greatly enhanced compared to traditional cavity-based sensors. In our proposal, two cavities couple to a dissipative reservoir at multiple points while they couple to a gain reservoir in a single-point way. To detecting a unknown parameter using this sensor, a waveguide is coupled to one of the cavities where detecting fields can pass through for homodyne detection. We find that multiple position-dependent couplings can induce an inherent non-reciprocal coupling between the cavities, which can enhance the performance of sensors. Output noise in our scheme can be reduced to the shot noise level, which is about one order magnitude lower than the results in Ref. [Lau and Clerk (2018)]. Besides, the signal-to-noise ratio per photon is also enhanced by about one order of magnitude. These results show that the multiple-point-coupling structure is beneficial to nowadays quantum devices. Copyright © 2022, The Authors. All rights reserved.

关键词： Couplings

Entity Representation Learning with Multimodal Neighbors for Link Prediction in Knowledge Graph

学校读者我要写书评

暂无评论

Entity Representation Learning with Multimodal Neighbors for...

International Conference on Computer and Communications (ICCC)

作者： Wenxuan Liu Hao Duan Zeng Li Jingdong Liu Hong Huo Tao Fang Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education of China China Shanghai Engineering Research Center of Intelligent Control and Management China

ISBN: (纸本)9781665409513

Entity representation learning is both fundamental and crucial for link prediction in knowledge graph. Existing entity representation learning approaches mainly focus on learning from knowledge triples with single modal text data which could only describe the things or concepts in words. However, multimodal data commonly exists in the real worlds and may describe things or concepts from different aspects. Therefore, multimodal entities have emerged in knowledge graph in recent years, which greatly enrich the knowledge graph by different information. This paper focuses on how to learn more robust and comprehensive representations of multimodal entities for better link prediction. A new representation learning method for multimodal entities is proposed, called Graph Attention with Bi-pooling Representation Learning (GBRL), where multimodal fusion and knowledge embedding are combined for learning representations of an entity with consideration of its multimodal neighbors. Firstly, feature vectors are obtained by pre-trained models for each modality. Then, the bilinear pooling is utilized for combining feature vectors of multimodal entities into multimodal feature vectors. A two-layer graph attention module is followed to generate multimodal representations of an entity from its multimodal neighbors. Finally, the inception decoder uses multimodal knowledge embedding to calculate scores for link prediction. The experimental results have shown that the proposed method performs well on link prediction by consideration of multimodal entities comparing with traditional methods that using only single modal text data.

关键词： Representation learning Knowledge representation Feature extraction Decoding

Arbitrary State Transition of Open Qubit System Based on Switching control

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Guangpu Xue, Shibei Ma, Shan Kuang, Sen Dong, Daoyi Petersen, Ian R. Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China School of Automation Central South University Changsha410083 China Department of Automation University of Science and Technology of China Hefei230027 China School of Engineering Australian National University CanberraACT2601 Australia

We present a switching control strategy based on Lyapunov control for arbitrary state transitions in open qubit systems. With coherent vector representation, we propose a switching control strategy, which can prevent the state of the qubit from entering invariant sets and singular value sets, effectively driving the system ultimately to a sufficiently small neighborhood of target states. In comparison to existing works, this control strategy relaxes the strict constraints on system models imposed by special target states. Furthermore, we identify conditions under which the open qubit system achieves finite-time stability (FTS) and finite-time contractive stability (FTCS), respectively. This represents a critical improvement in quantum state transitions, especially considering the asymptotic stability of arbitrary target states is unattainable in open quantum systems. The effectiveness of our proposed method is convincingly demonstrated through its application in a qubit system affected by various types of decoherence, including amplitude, dephasing and polarization decoherence. Copyright © 2024, The Authors. All rights reserved.

关键词： Asymptotic stability