检索结果-内蒙古大学图书馆

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

Distributed Task Allocation with Time Constraints Under Limited Communication Resources in Multi-Agent system

Distributed Task Allocation with Time Constraints Under Limi...

引用

Asian control Conference

作者： Weilin Li Jing Wu Chengnian Long Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

In this paper, a new distributed allocation algorithm based on performance impact with collective influence (PI-CI) is proposed. Considering inefficiency of creating time slots in PI-MaxAss, two completely independent phases with different communication frequencies are designed to ensure allocation both real-time and conflict-free under limited communication. To solve the misconvergence of the baseline algorithm PI-MaxAss in allocation results, an evaluation function is put forward in consensus phase to directly determines the final attribution of repeatedly assigned tasks, guaranteeing convergence of allocation. Comparison experiments validate the performance improvement of the PI-CI algorithm over the baseline algorithm.

关键词： Time-frequency analysis Real-time systems Resource management Time factors Multi-agent systems Radio spectrum management Convergence

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Correlation between Student Learning Behaviors and Academic Performance in Blended Learning Environments

Analyzing the Correlation between Student Learning Behaviors...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Ying Chen, Kang Xu, Zhezhuang Lin, Ye Zeng, Qingbo College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350368604

Blended learning integrates online and face-to-face (FTF) teaching methods to offer students in higher education a flexible and customized educational experience. Despite its significant advantages in promoting academic achievement and increasing student participation, blended learning presents challenges for educators due to difficulties in collecting and analyzing learning behavior data. Existing research mainly focuses on single learning modes, and data collection methods primarily rely on interviews and questionnaires, which can be subjective. To address these challenges, this study developed a mobile software called EasyClass, integrated with an online Small Private Online Course(SPOC) platform, to automatically record student behaviors in a blended learning environment. Obtaining data from an undergraduate blended learning course, statistical methods are used to analyze the correlation between student behaviors and final grades, as well as to identify factors affecting grades. The results of multivariate linear regression models confirmed the feasibility and effectiveness of blended instruction. This study provides a new approach to identifying and disseminating effective data collection strategies in blended learning, enabling educators and educational institutions to better understand and assess student behaviors, and to further explore their impact on final academic achievement. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Cooperative Optimization Method of UAV Swarm for Multi-objective High-Precision Location 5th

Cooperative Optimization Method of UAV Swarm for Multi-objec...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Li, Bowen Ji, Xiaoting Huang, Yuanling School of Information System Engineering Information Engineering University Zhengzhou450001 China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu610041 China

ISBN: (纸本)9789811939976

In the field of electromagnetic radiation source location, using UAVs to locate the radiation source target has become a new location method. At present, the UAV swarm cooperative optimization method for high-precision location has some challenges, such as insufficient ability of multi-objective high-precision location, poor timeliness and so on. To solve these problems, this paper proposes a cooperative optimization method of UAV swarm for multi-objective location. Firstly, the multi-objective joint location accuracy is derived, which is taken as the objective function of swarm cooperative optimization. Secondly, in order to allocate multiple UAVs to multiple targets efficiently, the initialization strategy based on target isolation and the random allocation method of UAV based on probability are proposed. Finally, by combining the above improved strategies, an optimization method of UAV swarm cooperative location is proposed. Through the analysis of experimental results, the cooperative optimization method in this paper has obvious advantages in global optimization and convergence ability, which can improve the joint location accuracy and optimization speed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning with GAN for Semantic Segmentation of Wood Defect image

Semi-supervised learning with GAN for Semantic Segmentation ...

引用

2024 China Automation Congress, CAC 2024

作者： Zheng, Kunxin Zheng, Song Xu, Zhezhuang Lin, Ye Zhu, Yuhang College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350368604

Automatic defect detection on wood surface is essential for ensuring product quality. Semantic segmentation methods have shown outstanding performance in wood defect detection. However, it is costly to acquire correct pixel-level labels of wood surface defects due to the complicated characteristics. To mitigate the cost of acquiring high-quality datasets, this study proposes a semi-supervised defect detection approach based on generative adversarial networks, which contains a generator and a discriminator. The generator is utilized to generate pixel-level segmentation results of wood defect images. To improve the segmentation performance, the discriminator learns against the generator by judging the goodness of the prediction results and generates supervised signals for the prediction results of unlabeled images. With this learning model, the proposed method can enhance segmentation performance using unlabeled images and alleviate the burden of data annotation. We validate the effectiveness of the proposed approach on a collected dataset of wood defects. Experimental results demonstrate the remarkable performance of our method even when utilizing only a small amount of annotated data. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Pointer Meter Reading under Noise Based on Virtual Data Generation

Pointer Meter Reading under Noise Based on Virtual Data Gene...

引用

2024 China Automation Congress, CAC 2024

作者： Zhu, Jinyang Xu, Zhezhuang Lin, Ye College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350368604

Using machine vision for meter reading significantly enhances the efficiency of industrial monitoring. However, meters in outdoor environment are often subject to the noise such as rain and fog, which affect the accuracy of meter readings. Additionally, the meter images and labels under noise are hard to obtain. To address these challenges, We propose a method for pointer meter reading under noise based on virtual data generation. Firstly, We utilize Unity to construct an industrial meter scene, which generates the images of meter under noise and theri labels. Secondly, we develop a U-Net network with an ASPP module, which expands the receptive field of network and enhances the ability of segmentation network to capture global semantic information under noise. Finally, the angular method is used to calculate the meter readings. Experimental results show that this method can effectively read meters under noise in outdoor environments. © 2024 IEEE.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Path Planning for Finite Horizon Tasks with Counting Time Temporal Logics

Multi-Agent Path Planning for Finite Horizon Tasks with Coun...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Peng Lv Shaoyuan Li Xiang Yin Department of Automation and Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

In this paper, we consider the multi-agent path planning problem for high-level tasks with finite horizons. In many situations, there is the need to count how many times a sub-task is satisfied in order to achieve the overall task. However, existing temporal logic languages, such as linear temporal logic, may not be efficient in describing such requirements. To address this issue, we propose a new temporal logic language called Counting Time Temporal Logic (CTTL) that extends linear temporal logic by explicitly counting the number of times that some tasks are satisfied. To solve the CTTL path planning problem, we use integer linear programming to encode the satisfaction of the task. We demonstrate that our approach is both sound and complete. To validate our results, we present numerical experiments to show the scalability of the proposed approach. Furthermore, we provide a simulation case study of a team of autonomous robots to illustrate the synthesis procedure.

关键词： Computer aided software engineering Automation Scalability Integer linear programming Path planning Planning Delays Logic Standards Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

Design Technology of Multi-AGV Warehouse Intelligent Scheduling Optimization control system 15th

Design Technology of Multi-AGV Warehouse Intelligent Schedul...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Pan, YanPeng Zhang, XueTing Zhang, FuQuan Tan, LiLi Yang, LiJie Ma, Jun China Academy of Launch Vehicle Technology Beijing100076 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9789819700677

Different from the traditional warehousing system, in the multi-AGV warehouse scheduling control system, the constraints of poor connectivity of the conveying track have led to the emergence of urgent problems such as vehicle conflicts in the task, low efficiency of multitasking concurrency, difficulty of delineating the conditions for entering the transporting area and so on. This paper proposes a design of multi-AGV warehouse intelligent scheduling optimized control system, which takes multitask scheduling research as an entry point, designs the warehouse layout and vehicle operation rules assumptions and modeling, studies the scheduling solution of Monorail Vehicles in multiple tasks, designs a scheduling optimization method based on the algorithm of Time Window, solves conflicts between key process and operation task process and optimize the scheduling, so as to effectively enhance the efficient scheduling capability of multi-AGV warehouse intelligent scheduling optimized control system. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Warehouses

来源：评论

学校读者我要写书评

暂无评论

Hybrid Traffic Scheduling Based on Adaptive Time Slot Slicing in Time-Sensitive Networking

Hybrid Traffic Scheduling Based on Adaptive Time Slot Slicin...

引用

2022 IEEE International Conference on Industrial Technology, ICIT 2022

作者： Wang, Shouliang Xu, Qimin Zhang, Yanzhou Xu, Lei Chen, Cailian Shanghai Jiao Tong University Department of Automation Shanghai China 200240 Key Laboratory of System Control and Information Processing Ministry of Education of China

ISBN: (纸本)9781728119489

The development of the Industrial Internet of Things (IIoT) is increasingly relying on the low-latency and low-jitter information exchange. Time-Sensitive Networking (TSN) guarantees the deterministic transmission by a set of mechanisms, such as Time-Aware Shaper (TAS) and Cyclic Queuing and Forwarding (CQF). However, the deterministic scheduling of hybrid traffic with different Quality of Service (QoS) is still unresolved since traffic performance is hard to meet by a single mechanism or an integrated mechanism with fixed time slot. In this paper, to realize the low-latency and low-jitter hybrid traffic scheduling, an adaptive time slot slicing (ATSS) method is proposed integrating TAS and CQF. With dynamically slicing the time slot to centralize time-triggered (TT) traffic, ATSS eliminates the irregular distribution of TT flow to support multi-hop networks. A resource calculation method based on slot occupancy judgment is devised to reduce the scheduling complexity, which raises the analysis objects into flows instead of frames. To reduce the complexity further, an incremental algorithm with the search boundary of resources is designed. The evaluation results show that ATSS reduces the jitter by 12 times and time cost by 200 times when handling over 125 mixed flows in different network topologies compared to previous work. © 2022 IEEE.

关键词： Jitter

来源：评论

学校读者我要写书评

暂无评论

Collision-Free Path Planning with Kinematic Constraints in Urban Scenarios

引用

Journal of Shanghai Jiaotong university(Science) 2021年第5期26卷 731-738页

作者： WANG Liang WANG Bing WANG Chunxiang Department of Automation Key Laboratory of System Control and Information Processing of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China

In urban driving scenarios,owing to the presence of multiple static obstacles such as parked cars and roadblocks,planning a collision-free and smooth path remains a challenging *** addition,the path-planning problem is mostly non-convex,and contains multiple local ***,a method for combining a sampling-based method and an optimization-based method is proposed in this paper to generate a collision-free path with kinematic constraints for urban *** sampling-based method constructs a search graph to search for a seeding path for exploring a safe driving corridor,and the optimization-based method constructs a quadratic programming problem considering the desired state constraints,continuity constraints,driving corridor constraints,and kinematic constraints to perform path *** experimental results show that the proposed method is able to plan a collision-free and smooth path in real time when managing typical urban scenarios.

关键词： autonomous vehicle path planning dynamic searching quadratic programming

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：