检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Pan, Yu Su, Zeyong Liu, Ao Wang, Jingquan Li, Nannan Xu, Zenglin Harbin Institute of Technology Shenzhen Shenzhen China University of Electronic Science and Technology of China Chengdu China Tokyo Institute of Technology Tokyo Japan State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Pengcheng Laboratory Shenzhen China

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight initialization methods. To be specific, general initialization methods, such as Xavier or Kaiming initialization, usually fail to generate appropriate weights for TCNNs. Meanwhile, although there are ad-hoc approaches for specific architectures (e.g., Tensor Ring Nets), they are not applicable to TCNNs with other tensor decomposition methods (e.g., CP or Tucker decomposition). To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs. Specifically, we first present the Reproducing Transformation to convert the backward process in TCNNs to an equivalent convolution process. Then, based on the convolution operators in the forward and backward processes, we build a unified paradigm to control the variance of features and gradients in TCNNs. Thus, we can derive fan-in and fan-out initialization for various TCNNs. We demonstrate that our paradigm can stabilize the training of TCNNs, leading to faster convergence and better results. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection of stealthy false data injection attacks against networked control systems via active data modification

引用

Information Sciences 2021年 546卷 192-205页

作者： Zhong-Hua Pang Lan-Zhi Fan Jian Sun Kun Liu Guo-Ping Liu Key Laboratory of Fieldbus Technology and Automation of Beijing North China University of Technology Beijing 100144 China State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing 100081 China Department of Artificial Intelligence and Automation Wuhan University Wuhan 430072 China

This paper investigates the design and detection problems of stealthy false data injection (FDI) attacks against networked control systems from the different perspectives of an attacker and a defender, respectively. First, a Kalman filter-based output tracking control system is presented, where stealthy FDI attacks are designed for its feedback and forward channels so as to destroy the system performance while bypassing a traditional residual-based detector. Second, to successfully detect such two-channel stealthy attacks, an active data modification scheme is proposed, by which the measurement and control data are amended before transmitting them through communication networks. Theoretical analysis is then carried out for both ideal and practical cases to evaluate the effectiveness of the detection scheme. An interesting finding is that the attacks designed based on a false model obtained from those modified data can remain stealthy. Finally, simulation results are provided to validate the proposed attack design and detection schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fusionplanner: A Multi-Task Motion Planner for Mining Trucks Using Multisensor Fusion Method

SSRN

引用

SSRN 2023年

作者： Teng, Siyu Chen, Long Li, Luxi Li, Yuchen Hu, Xuein Li, Lingxi Ai, Yunfeng Department of Computer Science Hong Kong Baptist University Hong Kong The School of Artificial Intelligence Hubei University Wuhan China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China Waytous Inc. Haidian Distinct Beijing China Indianapolis United States School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

In recent years, significant achievements have been made in motion planning for intelligent vehicles. However, as a typical unstructured environment, open-pit mining attracts limited attention due to its complex operational conditions and adverse environmental factors. A comprehensive paradigm for unmanned transportation in open-pit mines is proposed in this research, including a simulation platform, a testing benchmark, and a trustworthy and robust motion planner. Firstly, we introduce the Parallel Mining Simulator (PMS), a high-fidelity simulator specifically designed for open-pit mining scenarios. PMS enables to management and control of open-pit mine transportation from both the single-truck control and multi-truck scheduling perspectives. Then, we develop a novel benchmark called MiningNav, which offers three validation approaches suitable for transportation roads. The purpose of MiningNav is to evaluate the trustworthiness and robustness of algorithms in open-pit mines. Finally, we propose the first multi-task motion planning algorithm, called FusionPlanner, for the mining truck by the multisensor fusion method to adapt both lateral and longitudinal control tasks for unmanned transportation. We validate the performance of our planner using MiningNav in PMS, and empirical results demonstrate a significant reduction in the number of collisions and takeovers of FusionPlanner, thereby improving overall trustworthiness and robustness. © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Collaborative Scheduling of Computing Tasks for Edge Computing

Collaborative Scheduling of Computing Tasks for Edge Computi...

引用

Chinese automation Congress (CAC)

作者： Yue Liu Gang Xiong Fenghua Zhu Shichao Chen Liguo Zhang Xudong Liu School of Artificial Intelligence and Automation Beijing University of Technology The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation and the Cloud Computing Center Chinese Academy of Sciences Beijng China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation and Qingdao Academy of Intelligent Industries Chinese Academy of Sciences Beijng China Faculty of Information and Technology Beijing University of Technology Beijing China

ISBN: (纸本)9781665426480

In the face of the rapid development of the IoT, the traditional cloud computing, while providing services for mobile intelligent devices, also brings problems such as network bandwidth occupation and communication delay. Edge computing can solve these problems to some extent. But too many offloaded tasks may result in an edge server becoming overloaded and execution delay of tasks increasing, the computing resources of idle edge devices are also not fully utilized. In order to make full use of the computing resources of idle edge devices in the local network and reduce the execution delay for computing tasks, this paper takes the average delay time for all end devices as the optimization objective and proposes an end-edge cooperative scheduling (EECS) model to schedule tasks for edge computing. The scheduling algorithm used in EECS model is improved based on MCT algorithm. We use the EdgeCloudSim to verily the EECS model and scheduling algorithm. The simulation results show that the average completion time of computing tasks in EECS model, compared with only single edge server (SEE) task computing model, can be reduced by up to three times. In addition, the system load can be balanced to a certain extent in local network.

关键词： Analytical models Scheduling algorithms Computational modeling Collaboration Scheduling Delays Servers

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Completion by Larger Receptive Fields for Intelligent Vehicles

Point Cloud Completion by Larger Receptive Fields for Intell...

引用

International Conference on Intelligent Transportation

作者： Yunqing Zhang Xiaotong Zhang Kunhua Liu Yisheng Lv Wei He Long Chen School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China School of Mechanical and Automotive Engineering Qingdao University of Technology Qingdao China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Intelligence Science and Technology University of Science and Technology Beiing Beijing China Waytous Inc. Beijing China

Point cloud completion is a critical task for intelligent vehicles in the Intelligent Transportation systems (ITS). Due to the disordered nature of point clouds, current point-based point completion methods utilize max pooling operations and Convolutional Neural Networks (CNNs) with a convolution kernel size of 1 to extract point features. However, a network with a kernel size of 1 has a small receptive field and can only extract one point feature at a time; as a result, such a network struggles to precisely extract highly abstracted features. To address this issue, we propose a point cloud completion network with larger receptive fields, termed PLRF-Net, which is composed of two parts: a reconstruction network and a completion network. The reconstruction network focuses on repairing the structures of partial points and includes an offset-attention embedding module, a rearrangement module, several convolution layers with varying kernel sizes, a pooling and repeating layer, and transposed convolution layers with different kernel sizes. Meanwhile, the completion network strives to improve the precision of the completed point cloud and consists of several convolution layers, along with a downsampling and upsampling module. Experimental results indicate that our approach achieves superior quantitative and qualitative outcomes on both the Multiview Partial Point Cloud (MVP) and KITTI datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a novel flexible assistive hand exoskeleton

Design of a novel flexible assistive hand exoskeleton

引用

Youth Academic Annual Conference of Chinese Association of automation (YAC)

作者： Guotao Li Long Cheng Zhengrun Gao Jilong Lu Yanjiang Zhao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The National Clinical Research Center for Aging and Medicine Fudan University Shanghai China Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of Education Harbin University of Science and Technology Harbin China Intelligent Machine Institute Harbin University of Science and Technology Harbin China

ISBN: (纸本)9781665465373

Hand paralysis caused by stroke, spinal cord injury, or neurological trauma has a significant impact on the independence and quality of life of the patients. The hand exoskeleton can provide hand assistance and improve the patient’s grasp. In this article, a novel wearable flexible hand exoskeleton is proposed to assist users in activities of daily life. To create a simple and lightweight assistive hand exoskeleton, 3D printing is used to manufacture most of the components, and a remote drive system is designed to reduce the weight of the hand exoskeleton. A ball pair device and a slider device are used to ensure the freedom of the thumb and the adaptability of the hand exoskeleton to different hand sizes. Finally, the experiments are conducted to verify that the hand exoskeleton can achieve motion assistance.

关键词： Exoskeletons Thumb Metals Stroke (medical condition) Three-dimensional printing Motion capture Paralysis

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Algorithm for Convex Optimization with Coupled Constraints

arXiv

引用

arXiv 2022年

作者： Huang, Yi Zeng, Xianlin Meng, Ziyang Sun, Jian School of Automation Beijing Institute of Technology Beijing100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Department of Precision Instrument Tsinghua University Beijing100084 China Chongqing Innovation Center Beijing Institute of Technology Chongqing401120 China

This paper develops a distributed primal-dual algorithm via event-triggered mechanism to solve a class of convex optimization problems subject to local set constraints, coupled equality and inequality constraints. Different from some existing distributed algorithms with the diminishing step-sizes, our algorithm uses the constant step-sizes, and is shown to achieve an exact convergence to an optimal solution with an O(1/k) convergence rate for general convex objective functions, where k > 0 is the iteration number. Moreover, by applying event-triggered communication mechanism, the proposed algorithm can effectively reduce the communication cost without sacrificing the convergence rate. Finally, a numerical example is presented to verify the effectiveness of the proposed algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Online progressive instance-balanced sampling for weakly supervised object detection

arXiv

引用

arXiv 2022年

作者： Chen, Minghao Tian, Yunong Li, Zhishuo Li, En Liang, Zize The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China Yuquan Road Beijing100049 China Engineering Laboratory of Industrial Vision and Intelligent Equipment Technology Chinese Academy of Sciences 95 Zhongguancun East Road Beijing100190 China

Based on multiple instance detection networks (MIDN), plenty of works have contributed tremendous efforts to weakly supervised object detection (WSOD). However, most methods neglect the fact that the overwhelming negative instances exist in each image during the training phase, which would mislead the training and make the network fall into local minima. To tackle this problem, an online progressive instance-balanced sampling (OPIS) algorithm based on hard sampling and soft sampling is proposed in this paper. The algorithm includes two modules: a progressive instance balance (PIB) module and a progressive instance reweighting (PIR) module. The PIB module combining random sampling and IoU-balanced sampling progressively mines hard negative instances while balancing positive instances and negative instances. The PIR module further utilizes classifier scores and IoUs of adjacent refinements to reweight the weights of positive instances for making the network focus on positive instances. Extensive experimental results on the PASCAL VOC 2007 and 2012 datasets demonstrate the proposed method can significantly improve the baseline, which is also comparable to many existing state-of-the-art results. In addition, compared to the baseline, the proposed method requires no extra network parameters and the supplementary training overheads are small, which could be easily integrated into other methods based on the instance classifier refinement paradigm. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

TrajGen: Generating Realistic and Diverse Trajectories with Reactive and Feasible Agent Behaviors for Autonomous Driving

arXiv

引用

arXiv 2022年

作者： Zhang, Qichao Gao, Yinfeng Zhang, Yikang Guo, Youtian Ding, Dawei Wang, Yunpeng Sun, Peng Zhao, Dongbin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The College of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Baidu Inc. Beijing100085 China

Realistic and diverse simulation scenarios with reactive and feasible agent behaviors can be used for validation and verification of self-driving system performance without relying on expensive and time-consuming real-world testing. Existing simulators rely on heuristic-based behavior models for background vehicles, which cannot capture the complex interactive behaviors in real-world scenarios. To bridge the gap between simulation and the real world, we propose TrajGen, a two-stage trajectory generation framework, which can capture more realistic behaviors directly from human demonstration. In particular, TrajGen consists of the multi-modal trajectory prediction stage and the reinforcement learning based trajectory modification stage. In the first stage, we propose a novel auxiliary RouteLoss for the trajectory prediction model to generate multi-modal diverse trajectories in the drivable area. In the second stage, reinforcement learning is used to track the predicted trajectories while avoiding collisions, which can improve the feasibility of generated trajectories. In addition, we develop a data-driven simulator I-Sim that can be used to train reinforcement learning models in parallel based on naturalistic driving data. The vehicle model in I-Sim can guarantee that the generated trajectories by TrajGen satisfy vehicle kinematic constraints. Finally, we give comprehensive metrics to evaluate generated trajectories for simulation scenarios, which shows that TrajGen outperforms either trajectory prediction or inverse reinforcement learning in terms of fidelity, reactivity, feasibility, and diversity. Copyright © 2022, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Urban trip generation forecasting based on gradient boosting algorithm 1

Urban trip generation forecasting based on gradient boosting...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Li, Zhishuai Xiong, Gang Zhang, Yu Zheng, Meng Dong, Xisong Lv, Yisheng Institute of Automation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Municipal Institute of City Planning and Design Traffic Planning Department Beijing China

ISBN: (纸本)9781665433372

The four-step transportation model plays an important role in urban planning. The quality of the first phase, i.e. trip generation, determines the performance of the global course. The majority of trip generation forecasting models highly rely on mathematical derivation and have many predictor variables during the prediction, which leads to low accuracy of results and requires laboriously hand-crafted design of input vectors. This paper is the first to introduce the gradient boosting decision tree (GBDT) algorithm for trip generation prediction, and harmonizes such a powerful machine learning method with traditional urban planning requirements to achieve better prediction performance. Unlike the commonly used linear regression method, GBDT can automatically perform feature selection and model the non-linear relationships between input and output variables. Experimental results on real-world residential travel census in Beijing prove that the GBDT model significantly outperforms the baseline and can forecast the trip generation more accurately. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：