检索结果-内蒙古大学图书馆

第42届中国控制会议

作者： Wen Li Jinya Su Shihua Li School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University

In this study, we investigate the control problem of electronic throttle systems in the presence of practical challenges such as disturbances and measurement noises. To address these challenges, we propose an adaptive augmented Kalman filter(AAKF)based control approach that combines the strengths of extended state observer in disturbance estimation and adaptive Kalman filter in adaptive noise filtering. The outputs of AAKF are integrated into the Backstepping control design, resulting in a composite control that concurrently achieves fast disturbance rejection and noise suppression. We conduct a comparative simulation study against conventional methods without adaptive filtering to validate the effectiveness of the proposed AAKF-based control strategy, which exhibits superior position control accuracy and disturbance attenuation performance. We envision that our proposed control strategy will contribute to improving vehicle power, fuel economy, and emission performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accurate Detection and Tracking of Trucks and Truck Drivers

Ensuring Port Safety: Improved YOLOX and DeepSORT for Accura...

引用

第42届中国控制会议

作者： Xueqin Zheng Jinya Su Jun Yang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University

An optimized YOLOX+DeepSORT method is proposed to accurately detect and track container trucks and truck drivers at the working position of automated rubber tire gantries in ports, while ensuring their safety during the whole working *** the proposed method, the improved YOLOX performs object detection and its output is used as the input for multi-object tracking using DeepSORT. The improved YOLOX model is developed through replacing standard convolution with depthwise separable convolution, adding the convolutional block attention module to enhance feature extraction, and using Focal Loss in the loss function to address sample imbalances. Comparative experiments were carried out on a self-built dataset, showing a4.32% increase in mAP and improved reasoning speed for improved YOLOX compared to the original YOLOX. Furthermore,the optimized method shows a 3.57% increase in Multi-Object Tracking Accuracy and a 1.73% increase in Multi-Object Tracking Precision compared to the benchmark YOLOX+DeepSORT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An end-to-end instance segmentation method based on improved ConvNeXt V2

引用

International Journal of Wireless and Mobile Computing 2024年第4期26卷 384-392页

作者： Wang, Wenlu Sun, Ying Xu, Manman Bai, Dongxu Huang, Li Zou, Chunlong Chen, Baojia Tang, Dalai Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science and Technology Hubei Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China College of Mechanical Engineering Hubei University of Automotive Technology Hubei Shiyan China Hubei Key Laboratory of Hydroelectric Machinery Design and Maintenance China Three Gorges University Hubei Yichang China School of Computer Information Management Inner Mongolia University of Finance and Economics Hohhot China

In order to improve the efficiency of indoor mobile robots in locating and segmenting environmental instances, an instance segmentation method based on RTMDet is proposed. Firstly, the more powerful ConvNeXt V2 is used as the backbone network of the model, which improves the performance of the existing RTMDet model. Subsequently, NAS-FPN is used as a converged network to detect the network at any given time. Finally, AdamW is used as the model optimiser, which effectively solves the problem of excessive memory occupation when updating parameters and improves the performance of the model. The proposed method obtains the highest evaluation index in all cases. After training and testing on the Cityscapes data set, the recognition accuracy reaches 65.0%. © 2024 Inderscience Enterprises Ltd.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Autonomous Path Planning and Realization for Dual Robot Cooperation Based on ROS Framework

Autonomous Path Planning and Realization for Dual Robot Coop...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Jiawei Shao Yahui Gan Xianzhong Dai Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University NanJing China

To realize dual-robot autonomous path planning and realization, the trajectory planning research of dual-robot is carried out using the open-source robot operating system ROS as the simulation platform. The motion planning-related file configuration is completed by using MoveIt! In trajectory planning, cubic spline interpolation is performed on the trajectory points generated by the RRT-Connect path planning algorithm to complete the planning of the dual-arm assembly task. The communication between ROS nodes and ROS is established in the controller, and the processed trajectory points are communicated with the controller through ROS-Industrial. The experimental results show that the trajectory of the dual robot movement process is smooth and continuous, the stability is strong, and the error is small, which can ensure the completion of basic assembly tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv5 Detection Algorithm with Pruning and OpenVINO Quantization

An Improved YOLOv5 Detection Algorithm with Pruning and Open...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Cheng Gan, Yahui Han, Zao Gao, Huan Li, Ang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China

ISBN: (纸本)9798350303759

In order to address the problem of current object detection models being too large to be deployed on robot controllers, this paper proposes improvements to YOLOv5 for real-time detection. The YOLOv5s model is pruned at the Batch Normalization (BN) layer, and further optimized using the OpenVINO tool for quantization. The results demonstrate that our improvements effectively improve the model's inference speed while maintaining its accuracy. Compared to the original YOLOv5 model, the pruned model achieves the same accuracy without degradation, with a 36.6% reduction in parameter count and a 35% reduction in weight storage file size. Furthermore, after optimization with OpenVINO, the final model achieves a FPS of 56. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Research on Evolutionary Guiding Strategy for Self-organized Aggregates of Massive Flexible Resources 4

Research on Evolutionary Guiding Strategy for Self-organized...

引用

4th International Conference on Advanced Electrical and Energy systems, AEES 2023

作者： Mao, Tingfeng Zhang, Kaifeng Yin, Changwei Pan, Xiaohui Ma, Nan Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing210096 China Nanjing Power Supply Company of State Grid Jiangsu Electric Power Co. Ltd. Nanjing210019 China

ISBN: (纸本)9798350342659

With the improvement of communication technology and the management of demand-side, more and more researches focus on the aggregation technology of flexible resources on the demand side. This paper proposes to build a self-organizing response framework in the scenario of massive resources, and resources can independently choose to join or exit the aggregates to participate in the regulation of grid active power balance. However, self-organizing aggregates cannot generate aggregation scenarios that accurately match the dynamic needs of the power grid during autonomous operation, so the grid needs to further guide the evolution of the aggregates. Firstly, the process and principle of realizing self-organization and evolution of resources in cyberspace are outlined. Then, the evolutionary driving sources of the self-organizing aggregates are analyzed to construct the evolutionary dynamics model framework from both the steady and the dynamic dimensions, and the data-driven modeling is carried out through the back propagation neural network to obtain the evolution law of resource self-organization. Finally, an iterative evolutionary guiding strategy based on price feedback is designed. The optimal guiding value of the market price cap is obtained through iteration under the expected aggregation scale target of the power grid, and also the dynamic evolution time of the aggregates is predicted to determine the timing of the release of the guiding strategy. The proposed strategy is constructed and tested on the NETLOGO resource self-organization simulation platform. The results show that the self-organizing aggregates can evolve to the expected state of power grid demand with high accuracy. © 2023 IEEE.

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Semantic Map Construction via Multi-sensor Fusion 36

Semantic Map Construction via Multi-sensor Fusion

引用

36th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2021

作者： Qiu, Houhan Lin, Zhicheng Li, Jun Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9781665437127

Semantic SLAM can achieve the acquisition of environmental semantic information and increase the understanding of the environmental content. Therefore, it has received extensive attention from academia and industry. In the most existing work, the visual SLAM and deep learning algorithms are combined, and the point cloud fusion method is used to build maps. It is difficult to be directly applied to robot navigation due to problems of time misalignment of sensor data, mismatched detection ranges, and inconsistent accuracy. In this paper, a method of building a semantic map is proposed by combining lidar, camera, odometer. First, the semantic information and position information of the target object are obtained by the YOLO v3 algorithm through the camera, and the grid map is constructed by using the Gmapping algorithm. Second, the semantic information and position information are merged into the grid semantic map to form a semantic grid map. Finally, the effectiveness and feasibility of this method are verified by these experiments. © 2021 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

A Pursuit Strategy for Multi-Agent Pursuit-Evasion Game via Multi-Agent Deep Deterministic Policy Gradient Algorithm

A Pursuit Strategy for Multi-Agent Pursuit-Evasion Game via ...

引用

2022 IEEE International Conference on Unmanned systems, ICUS 2022

作者： Ye, Jianfeng Wang, Qing Ma, Bei Wu, Yongbao Xue, Lei School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China SEU-Monash Joint Graduate School Southeast University Nanjing China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

This paper studies a classical pursuit-evasion problem. The pursuer attempts to capture the faster evader in a bounded area. The velocity of evader is 1.2 times as fast as the pursuers'. All of them have adaptive strategies. We use game theory to model the multi-agent pursuit-evasion game and prove that the game model has Nash equilibrium. Then, we modify the multi-agent deep deterministic policy gradient (MADDPG) algorithm for seeking the Nash equilibrium. The simulation examples are given to illustrate the effectiveness of the designed method. © 2022 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter Adaptive Speed Tracking control for High-speed Trains with Noise Interference

Kalman Filter Adaptive Speed Tracking Control for High-speed...

引用

IEEE International Conference of Intelligent Robotic and control engineering (IRCE)

作者： Chunli Zhang Yuwei Xie Lei Yan Fucai Qian College of Automation and Information Engineering Xi’an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an China

ISBN: (数字)9798350352399

ISBN: (纸本)9798350352405

In this paper, high-speed train is regarded as a single prime point, a new tracking control method combining adaptive control and Kalman filtering is proposed. This paper solves the noise interference problem in the tracking control process of high-speed train. The method first linearises the original system, then uses Kalman filtering to do model estimation, and the controller is designed for the predictive model through adaptive control. Finally, MATLAB is used to simulate and verify the effectiveness of this method. This proposed method successfully solves the problems of nonlinearity, noise interference and unknown parameters in system. The error caused by resistance in the high-speed train tracking control process can be dealt with effectively.

关键词： Resistance Filtering Noise Process control Interference Predictive models Mathematical models Kalman filters Adaptive control MATLAB

来源：评论

学校读者我要写书评

暂无评论

Adaptive SOM neural network algorithm 3

Adaptive SOM neural network algorithm

引用

3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing, AIAHPC 2023

作者： Wang, Xin Yan, Taishan School of Information Science and Engineering Hunan Institute of Science and Technology Hunan Yueyang China Hunan Institute of Science and Technology School of Information Science and Engineering China Key Laboratory of Hunan Province on Intelligent Control and Optimization of Complex Industrial Logistics System Hunan Yueyang China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

In order to improve the performance of traditional SOM model, an adaptive SOM neural network algorithm is proposed. By introducing the error square sum solution formula, the clustering error of the model sub-data set is calculated by using the method of cutting the data set, and the change trend of the clustering error is quickly obtained. Then the learning rate of the SOM network is adaptively adjusted according to this, and the convergence speed is accelerated on the basis of ensuring that the network is fully trained, thereby improving the performance of the SOM network. © 2023 SPIE.

关键词： Errors

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：