检索结果-内蒙古大学图书馆

第40届中国控制会议

作者： Bing Wu Zhijun Xue Wenjie Chen State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center

Recently,unmanned aerial vehicles are widely used in surveillance,aerial photography,power grid line inspections and other *** order to deploy the YOLOv3[1] algorithm on drones,it is necessary to adopt the YOLOv3 algorithm with fewer parameters and a simpler *** paper implements the model compression of YOLOv3 based on methods such as sparseness,pruning,and knowledge *** paper implements the sparseness of the network by adding L1 regular expressions on the convolutional *** that,redundant channels and layers are removed through channel pruning and layer *** sparse and pruning,the mAP lost a *** using knowledge distillation after pruning,it attempts to recover mAP lost in sparseness and *** this method,the YOLOv3 algorithm can be deployed on embedded platforms such as RK3399 *** evaluate the model on the visdrone2019 *** experimental results show that after model compression,YOLOv3 is more suitable for deployment on embedded platforms.

关键词： Object Detection Model Compress RK3399pro YOLOv3

来源：评论

学校读者我要写书评

暂无评论

A Cell Potential and Motion Pattern Driven Multi-robot Coverage Path Planning Algorithm 14th

A Cell Potential and Motion Pattern Driven Multi-robot Cover...

引用

14th International Conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Xu, Meng Xin, Bin Dou, Lihua Gao, Guanqiang School of Automation State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9789811534249

This paper proposes an intelligent "Cell Potential and Motion Pattern driven Coverage (CPMPC)" algorithm to solve a cooperative coverage path planning problem for multiple robots in two-dimensional target environment. The target environment is divided into cell areas according to the detection range of robot, and the cell matrix is given correspondingly. The values in the cell matrix are defined as cell potential, which represents the number of times each cell is detected by robots. The priority of the robot’s neighbor cell is called the motion pattern. At different moments, robots can choose within different motion patterns. Genetic algorithm (GA) is used to optimize the combination of motion patterns. By taking account obstacle avoidance and collision avoidance into consideration, the CPMPC algorithm adopts a double-layer choice strategy driven by cell potential and motion pattern to generate the next waypoint. Furthermore, this algorithm contains two optimal strategies: avoiding collision and jumping out of the detected area. Compared with the pattern-based genetic algorithm, the results obtained by us show that the CPMPC algorithm could solve the multi-robot coverage path planning (MCPP) problem effectively with guarantee of complete coverage, and improved makespan. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

An IoT Edge Computing System Architecture and its Application

An IoT Edge Computing System Architecture and its Applicatio...

引用

2020 IEEE International Conference on Networking, Sensing and control, ICNSC 2020

作者： Chen, Shichao Li, Qijie Zhang, Hua Zhu, Fenghua Xiong, Gang Tang, Ying Macau University of Science and Technology State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences China Beijing University of Technology State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Aerospace Smart Manufacturing Technology Development Co. Ltd Platform Research and Development Department Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Engineering Research Center of Intelligent Systems and Technology Institute of Automation Cloud Computing Center Chinese Academy of Sciences Beijing China Rowan University Department of Electrical and Computer Engineering GlassboroNJ United States Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China

ISBN: (纸本)9781728168531

As the number of devices connected to the Internet of things (IoT) surges, the amount of data explodes. Therefore it not only increases the bandwidth load of data transmission but also aggravates the computing and storage load of a cloud platform. At the same time, the traditional computing paradigm centered on cloud computing cannot meet the real-time requirements in many application scenarios. The emergence of edge computing can solve the problems of realtime data processing and network bandwidth occupation in the current IoT scene. In this paper, according to the characteristics of IoT, such as fragmented data, heterogeneous network, and limited energy consumption, the architecture of an IoT edge computing system is constructed to suit better an IoT scene. In addition, the application of edge computing key technologies such as virtualization, edge intelligence, computing offload, collaborative scheduling and micro-services in resource-constrained IoT scenarios is analyzed in detail. Finally, the functions and application of energy consumption monitoring and optimization to a central air-conditioning system are analyzed and summarized, which is a typical application of edge computing in the context of the IoT. © 2020 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Fast control Strategy of Grid-forming Inverter Based on Power Feedforward

Fast Control Strategy of Grid-forming Inverter Based on Powe...

引用

第42届中国控制会议

作者： Sheng Zhang Zhijian Fang Qine Liu Muchao Xiang Dingbang Huang School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education State Grid Hubei Electric Power Co. LtdXiangyang Power Supply Company Electric Power Scientific Research Institute of State Grid Hubei Electric Power Co. Ltd

Grid-forming inverter is widely used in grid-connected systems of distributed generation because of its frequency and voltage support capacity and good stability in microgrid,but its large inertia will affect the dynamic response speed of grid-forming *** order to solve this problem,this paper introduces the loop that affects the dynamic response of grid-forming inverter,and carries out small signal modeling for active loop,analyzes the dynamic performance indicators and determinants of typical second-order ***,a method of adding power feedforward coefficient to the forward channel of the power loop is designed,and the response speed of the system with or without feedforward coefficient under the unit step response is ***,the simulation results show that adding the power feedforward coefficient can improve the response speed of the grid-forming inverter during startup and power switching,then achieves the effect of fast control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Approximate optimal control of nonlinear systems with mismatched perturbations based on asymptotically stable critic neural network 2020

Approximate optimal control of nonlinear systems with mismat...

引用

6th International Conference on Computing and Data Engineering, ICCDE 2020 and 2020 International Conference on Artificial Intelligence in Electronics Engineering, AIEE 2020

作者： Zhao, Bo Hou, Jiaxu Guo, Ping Liu, Derong Xu, Yancai School of Systems Science Beijing Normal University Beijing100875 China School of Automation Guangdong University of Technology Guangzhou510006 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781450376730

In this paper, the approximate optimal control problem for nonlinear systems with mismatched perturbations is addressed through asymptotically stable critic neural network (NN). By employing the estimated perturbation via nonlinear perturbation observer, the online updated value function is constructed to reflect the real-time perturbations, regulation and control simultaneously. In order to solve the Hamilton-Jacobi-Bellman equation, an asymptotically stable critic NN is established based on the novel nested update laws. Thus, the approximate optimal control is obtained to guarantee the closed-loop system to be uniformly ultimately bounded based on the Lyapunov's direct method. Simulation results illustrate the effectiveness of the developed control scheme. © 2020 ACM International Conference Proceeding Series. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

InTEn-LOAM: Intensity and Temporal Enhanced LiDAR Odometry and Mapping

arXiv

引用

arXiv 2022年

作者： Li, Shuaixin Tian, Bin Xiaozhou, Zhu Jianjun, Gui Wen, Yao Li, Guangyun The National Innovation Institute of Defence Technology PLA Academy of Military Sciences Beijing100079 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science Beijing100081 China The Department of Geospatial Information PLA Information Engineering University Zhengzhou450001 China

Traditional LiDAR odometry (LO) systems mainly leverage geometric information obtained from the traversed surroundings to register laser scans and estimate LiDAR ego-motion, while it may be unreliable in dynamic or unstructured environments. This paper proposes InTEn-LOAM, a low-drift and robust LiDAR odometry and mapping method that fully exploits implicit information of laser sweeps (i.e., geometric, intensity, and temporal characteristics). Scanned points are projected to cylindrical images, which facilitate the efficient and adaptive extraction of various types of features, i.e., ground, beam, facade, and reflector. We propose a novel intensity-based points registration algorithm and incorporate it into the LiDAR odometry, enabling the LO system to jointly estimate the LiDAR ego-motion using both geometric and intensity feature points. To eliminate the interference of dynamic objects, we propose a temporal-based dynamic object removal approach to filter them out before map update. Moreover, the local map is organized and downsampled using a temporal-related voxel grid filter to maintain the similarity between the current scan and the static local map. Extensive experiments are conducted on both simulated and real-world datasets. The results show that the proposed method achieves similar or better accuracy w.r.t the state-of-the-arts in normal driving scenarios and outperforms geometric-based LO in unstructured environments. © 2022, CC BY.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

A non-interactive verifiable computation model of perceptual layer data based on CP-ABE 2

A non-interactive verifiable computation model of perceptual...

引用

2nd International Conference on Consumer Electronics and Computer Engineering, ICCECE 2022

作者： Zhao, Jianming Miao, Weiwei Zeng, Zeng Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China State Grid Jiangsu Electric Power Co. Ltd. Information Telecommunication Branch Nanjing China

ISBN: (纸本)9781665408868

The computing of smart devices at the perception layer of the power Internet of Things is often insufficient, and complex computing can be outsourced to server resources such as the cloud computing, but the allocation process is not safe and controllable. Under special constraints of the power Internet of Things such as multi-users and heterogeneous terminals, we propose a CP-ABE-based non-interactive verifiable computation model of perceptual layer data. This model is based on CP-ABE, NPOT, FHE and other relevant safety and verifiable theories, and designs a new multi-user non-interactive secure verifiable computing scheme to ensure that only users with the decryption key can participate in the execution of NPOT Scheme. In terms of the calculation process design of the model, we gave a detailed description of the system model, security model, plan. Based on the definition given, the correctness and safety of the non-interactive safety verifiable model design in the power Internet of Things environment are proved, and the interaction cost of the model is analyzed. Finally, it proves that the CP-ABE-based non-interactive verifiable computation model for the perceptual layer proposed in this paper has greatly improved security, applicability, and verifiability, and is able to meet the security outsourcing of computing in the power Internet of Things environment. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Research on cloud-side collaborative task migration strategy based on simulated annealing-Bee Colony Algorithm in Power IoT 2

Research on cloud-side collaborative task migration strategy...

引用

2nd International Conference on Consumer Electronics and Computer Engineering, ICCECE 2022

作者： Zhang, Bowen Zeng, Zeng Miao, Weiwei Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang China State Grid Jiangsu Electric Power Co. Ltd. Information Telecommunication Branch Nanjing China

ISBN: (纸本)9781665408868

In the power IoT, in order to make up for the shortcomings of insufficient computing capabilities of edge-side devices, cloud-side collaboration technology has attracted more and more attention. The cloud-side collaboration technology relies on the selection of task migration strategies. However, when the existing migration strategies face the complex edge-side terminal devices in the power IoT, the energy consumption and delay performance are not good enough, which greatly affects the user's power experience. Therefore, it is very valuable to study a cloud-side collaborative task migration strategy under the power IoT environment. This paper proposes a task migration strategy based on simulated annealing-Bee Colony Algorithm in the environment of power IoT, which can solve the problem of task migration. Experimental results show that compared with the existing popular methods, this method has advantages in terms of energy consumption and time delay. This research can meet the real-time requirements of the power IoT, while reducing energy consumption and improving the user's power experience, thereby promoting the further development of the power IoT. © 2022 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

GotFlow3D: Recurrent Graph Optimal Transport for Learning 3D Flow Motion in Particle Tracking

arXiv

引用

arXiv 2022年

作者： Liang, Jiaming Xu, Chao Cai, Shengze Hangzhou310027 China The State Key Laboratory of Industrial Control Technology The National Engineering Center for Industrial Automation The Institute of Cyber-Systems & Control at ZJU ZJU Huzhou Institute China The Institute of Cyber-Systems & Control College of Control Science & Engineering Zhejiang University Hangzhou310027 China

Flow visualization technologies such as particle tracking velocimetry (PTV) are broadly used in understanding the all-pervasiveness three-dimensional (3D) turbulent flow from nature and industrial processes. Despite the advances in 3D acquisition techniques, the developed motion estimation algorithms in particle tracking remain great challenges of large particle displacements, dense particle distributions and high computational cost. By introducing a novel deep neural network based on recurrent Graph Optimal Transport, called GotFlow3D, we present an end-to-end solution to learn the 3D fluid flow motion from double-frame particle sets. The proposed network constructs two graphs in the geometric and feature space and further enriches the original particle representations with the fused intrinsic and extrinsic features learnt from a graph neural network. The extracted deep features are subsequently utilized to make optimal transport plans indicating the correspondences of particle pairs, which are then iteratively and adaptively retrieved to guide the recurrent flow learning. Experimental evaluations, including assessments on numerical experiments and validations on real-world experiments, demonstrate that the proposed GotFlow3D achieves state-of-the-art performance against both recently-developed scene flow learners and particle tracking algorithms, with impressive accuracy, robustness and generalization ability, which can provide deeper insight into the complex dynamics of broad physical and biological systems. © 2022, CC BY.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

S$^{\text{4}}$TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年第2期9卷 3220-3231页

作者： Xiao Wang Ke Tang Xingyuan Dai Jintao Xu Quancheng Du Rui Ai Yuxiao Wang Weihao Gu Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei China Haomo Technology Company Ltd. Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S $^{\text{4}}$ TP) framework. Specifically, S $^{\text{4}}$ TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV's planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S $^{\text{4}}$ TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs' trajectories as input. With the integration of SADRF, S $^{\text{4}}$ TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S $^{\text{4}}$ TP in terms of safety and rationality. S $^{\text{4}}$ TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%.

关键词： Trajectory Safety Vehicles Trajectory planning Autonomous vehicles Risk management Behavioral sciences

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：