检索结果-内蒙古大学图书馆

第43届中国控制会议

作者： Yu Lin Jiayu Zou Kuo Wang Hai-Tao Zhang School of Artificial Intelligence and Automation Engineering Research Center of Autonomous Intelligent Unmanned Systems and the State Key Lab of Digital Manufacturing Equipment and TechnologyHuazhong University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper proposes a distributed control strategy for the composite disturbance problem in multimanipulator ***,the disturbance observer is used for the access to observe the composite disturbance and motion state of the *** a slide mode control law is developed to improve the accuracy of the tracking ***,sufficient conditions are derived to guarantee asymptotical convergency of the developed control ***,the numerical simulations are conducted to verify the effectiveness of the present control scheme.

关键词： Multi-manipulator systems sliding mode control composite disturbance the disturbance observer

来源：评论

学校读者我要写书评

暂无评论

Learning to Solve Multi-AGV Scheduling Problem with Pod Repositioning Optimization in RMFS

Learning to Solve Multi-AGV Scheduling Problem with Pod Repo...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Xuan Zhou Xiang Shi Wenqing Chu Jingchen Jiang Lele Zhang Fang Deng State Key Lab of Autonomous Intelligent Unmanned Systems School of Automation Beijing Institute of Technology Beijing China Beijing Institute of Technology Chongqing Innovation Center Chongqing China

ISBN: (数字)9798350340266

ISBN: (纸本)9798350340273

This paper studies a novel non-deterministic polynomial-hard (NP-hard) warehouse optimization problem, the multi-automated guided vehicle (multi-AGV) scheduling problem with pod repositioning optimization (MAS-PR), in a robotic mobile fulfillment system (RMFS). A major challenge in MAS-PR is that the storage assignment of pods and the task allocation decision of AGVs are closely coupled. To address this problem, an end-to-end Problem-Specific Mask-based Deep Reinforcement Learning (PSMDRL) method is proposed in this paper. In PSMDRL, we transform the MAS-PR into a Markov Decision Process (MDP) model, and then use an attention-based network model to learn the efficient allocation and retrieval policy. A mask strategy with problem-specific knowledge and a model structure with decoder embedding are designed to further improve the efficiency and effectiveness. Experimental results demonstrate that the proposed PSMDRL is more effective and efficient than the representative algorithms in solving the MAS-PR problem.

关键词： Service robots Computational modeling Transforms Deep reinforcement learning Path planning Decoding Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Task Scheduling for ICN-Based Computing First Network: A Deep Reinforcement Learning Approach 8

Task Scheduling for ICN-Based Computing First Network: A Dee...

引用

8th IEEE International Conference on Computer and Communications, ICCC 2022

作者： Zou, Zhuang Xie, Renchao Ren, Yuzheng Yu, F. Richard Huang, Tao Beijing University of Posts and Telecommunications State Key Lab. of Networking and Switching Technology Beijing China Carleton University Depart. of Systems and Computer Eng. OttawaON Canada

ISBN: (纸本)9781665450515

The computing first network (CFN) combines heterogeneous computing force information with network information and improves resource utilization and task execution efficiency through resource perception, service positioning, and task scheduling. However, since the heterogeneous computing force is difficult to express and perceive, and it is distributed on each node of the edge network, it is difficult to schedule tasks uniformly. Therefore, this paper proposes a CFN architecture based on information-centric network (ICN), which uses the naming mechanism of ICN to characterize the computing force and tasks, and the caching mechanism and routing and forwarding mechanism to improve the computing efficiency in the network. Under this network architecture, we study the scheduling problem of multi-user tasks in a period, model it as a multi-objective optimization model, and transform it into a Markov decision process (MDP) to enable control nodes to prioritize tasks and then schedule them to computing nodes for execution, which takes into account the task queue status and node resources. To solve the proposed problem, we use the deep reinforcement learning algorithm to approximate the optimal task scheduling solution. Finally, extensive simulation experiments are conducted to validate the effectiveness and superiority of the proposed scheme. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Image Captioning Considering Wasserstein Graph Matching

arXiv

引用

arXiv 2024年

作者： Yang, Yang The Nanjing University of Science and Technology Nanjing210094 China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China Ministry of Education State Key Lab. for Novel Software Technology Nanjing University China

Image captioning can automatically generate captions for the given images, and the key challenge is to learn a mapping function from visual features to natural language features. Existing approaches are mostly supervised ones, i.e., each image has a corresponding sentence in the training set. However, considering that describing images always requires a huge of manpower, we usually have limited amount of described images (i.e., image-text pairs) and a large number of undescribed images in real-world applications. Thereby, a dilemma is the "Semi-Supervised Image Captioning". To solve this problem, we propose a novel Semi-Supervised Image Captioning method considering Wasserstein Graph Matching (SSIC-WGM), which turns to adopt the raw image inputs to supervise the generated sentences. Different from traditional single modal semi-supervised methods, the difficulty of semi-supervised cross-modal learning lies in constructing intermediately comparable information among heterogeneous modalities. In this paper, SSIC-WGM adopts the successful scene graphs as intermediate information, and constrains the generated sentences from two aspects: 1) inter-modal consistency. SSIC-WGM constructs the scene graphs of the raw image and generated sentence respectively, then employs the wasserstein distance to better measure the similarity between region embeddings of different graphs. 2) intra-modal consistency. SSIC-WGM takes the data augmentation techniques for the raw images, then constrains the consistency among augmented images and generated sentences. Consequently, SSIC-WGM combines the cross-modal pseudo supervision and structure invariant measure for efficiently using the undescribed images, and learns more reasonable mapping function. Experiments show that our method can outperform state-of-the-art comparison methods on the MS-COCO "Karpathy" offline test split, under different complex semi-supervised scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Forming Circle Formations of Multi-agent systems Under Actuator Faults 5th

Forming Circle Formations of Multi-agent Systems Under Actu...

引用

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

作者： Liu, Jiajun Ru, Xinfeng Xia, Weiguo Wang, Chen China National Aeronautical Radio Electronic Research Institute and National Key Laboratory of Science and Technology on Avionics System Integration Shanghai China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering Dalian University of Technology Dalian China National Engineering Research Center of Software Engineering and the State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China

ISBN: (纸本)9789811939976

A distributed fault-tolerant formation control law is designed in this paper for multi-agent systems under external disturbances and actuator faults including time-varying loss of effectiveness faults. The initial position of each agent is already on a circle and the control purpose is to form a desired formation on this circle. Based on this local information, a distributed adaptive formation control law is designed by employing the congelation of variables method to deal with time-varying actuator faults. Finally, a simulation example is given to verify the effectiveness of the adaptive fault-tolerant control design method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Learning Instructions with Unlab.led Data for Zero-Shot Cross-Task Generalization

Learning Instructions with Unlabeled Data for Zero-Shot Cros...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Gu, Yuxian Ke, Pei Zhu, Xiaoyan Huang, Minlie The CoAI group Tsinghua University Beijing China Institute for Artificial Intelligence State Key Lab of Intelligent Technology and Systems Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing China

Training language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive collection of tasks described via human-craft instructions, has been shown effective in instruction learning for unseen tasks. However, IT relies on a large amount of human-annotated samples, which restricts its generalization. Unlike lab.led data, unlab.led data are often massive and cheap to obtain. In this work, we study how IT can be improved with unlab.led data. We first empirically explore the IT performance trends versus the number of lab.led data, instructions, and training tasks. We find it critical to enlarge the number of training instructions, and the instructions can be underutilized due to the scarcity of lab.led data. Then, we propose Unlab.led Data Augmented Instruction Tuning (UDIT) to take better advantage of the instructions during IT by constructing pseudo-lab.led data from unlab.led plain texts. We conduct extensive experiments to show UDIT's effectiveness in various scenarios of tasks and datasets. We also comprehensively analyze the key factors of UDIT to investigate how to better improve IT with unlab.led data. The code is publicly availab.e at https://***/thu-coai/UDIT. © 2022 Association for Computational Linguistics.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Semantic Segmentation with Contrastive Translation Coding 6th

Unsupervised Semantic Segmentation with Contrastive Translat...

引用

6th International Conference on Cognitive systems and Signal Processing, ICCSIP 2021

作者： Chen, Runfa Sun, Hanbing Wang, Ling State Key Lab on Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China Department of Air Defense Early Warning Command System Air Force Early Warning Academy Wuhang China

ISBN: (纸本)9789811692468

The proposed new method constructs a contrastive learning task through unsupervised image-to-image translation and indirectly extracts domain-invariant features by maximizing mutual information. Specifically, by reusing the semantic segmentation network for image-to-image translation, the probability space of the segmentation output is projected into the RGB space, thereby constructing positive and negative samples to maximize the mutual information between the input image and the semantic segmentation RGB projection map. Meanwhile, the output space of the target domain is transferred to the source domain, and then the robust domain-invariant semantic features are extracted. We develop two adversarial transfer methods and a three-stage training paradigm of pre-training, cross-domain transfer, and self-supervised training. Experiments on benchmarks demonstrate that this method is reasonable and feasible. Comprehensive ablation studies and analyses are also carried out to reveal the advantages and disadvantages of the two designed transfer schemes and the effect and significance of color-invariant semantic information for unsupervised semantic segmentation tasks. The contrastive learning task, which is constructed through unsupervised cross-domain image-to-image translation, provides a new insight for cross-domain transfer learning to overcome the problem of domain shift. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Cascade Extended state Observer with Sliding Mode Control in Application to Active Magnetic Bearing systems

Cascade Extended State Observer with Sliding Mode Control in...

引用

第43届中国控制会议

作者： Haichao Jiao Ran Shi Ziheng Yu Hai-Tao Zhang School of Artificial Intelligence and Automation Engineering Research Center of Autonomous Intelligent Unmanned Systems and the State Key Lab of Digital Manufacturing Equipment and TechnologyHuazhong University of Science and Technology Alibaba

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Given the high nonlinearity of the Active magnetic bearing(AMB) system,to achieve stable levitation,this paper proposes a closed-loop control strategy that integrates a cascade extended state observer(CESO) and a sliding mode controller(SMC). This approach addresses the constraints posed by high-frequency noise in the conventional extended state observer(ESO).The Bounded Input,Bounded Output stability(BIBO) of the AMB closed-loop control system is demonstrated through Lyapunov equation. Ultimately,simulation results confirm that CESO effectively suppresses the amplification of sensing noise compared to conventional ESO,while improving the observation precision of the observer and the control precision of the controller.

关键词： Active magnetic bearing system(AMB) cascade extended state observer(CESO) sliding mode controller(SMC) noise suppression

来源：评论

学校读者我要写书评

暂无评论

Suppression of self-pulsing in high power Tm3+-doped fiber laser

Suppression of self-pulsing in high power Tm3+-doped fiber l...

引用

2023 Advanced Fiber Laser Conference, AFL 2023

作者： Shen, Shiteng Dong, Fanlong Yan, Peiguang Wang, Jingzhang Lue, Qitao Guo, Chunyu Ruan, Shuangchen Shenzhen Key Laboratory of Laser Engineering Guangdong Provincial Key Laboratory of Micro/Nano Optomechatronics Engineering Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province State Key Laboratory of Radio Frequency Heterogeneous Integration College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen518060 China Key Lab. of Adv. Optical Precision Manufacturing Technology of Guangdong Higher Education Institutes Shenzhen Technology University Shenzhen518118 China Han s Laser Technology Industry Group Co. Ltd Shenzhen518057 China

ISBN: (纸本)9781510677661

In this paper, a high power Tm3+-doped fiber laser (TDFL) based on a monolithic master oscillator power amplifier (MOPA) system with the center wavelength is 1940 nm is demonstrated. The maximum laser power was measured to be 200 W with a slope efficiency of 56.2% at the 793 nm pump power of 368.6 W. Power stability of the laser output over 60 min is measured to be ∼0.12%, which indicate a relatively stable laser operation of the TDFL. The output power is limited by the availab.e pump power for the lack of amplified spontaneous emission, parasitic oscillation or self-pulsing effects even at the maximum output power level, showing further power scaling should be possible with increase the pump power. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Fiber lasers

来源：评论

学校读者我要写书评

暂无评论

Mid-infrared conventional solitons and soliton molecules in a polarization-maintaining fluoride fiber oscillator

Mid-infrared conventional solitons and soliton molecules in ...

引用

2023 Advanced Fiber Laser Conference, AFL 2023

作者： Zeng, Qinghui Yu, Linpeng Yan, Peiguang Wang, Jinzhang Lue, Qitao Guo, Chunyu Ruan, Shuangchen Shenzhen Key Laboratory of Laser Engineering Guangdong Provincial Key Laboratory of Micro/Nano Optomechatronics Engineering Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province State Key Laboratory of Radio Frequency Heterogeneous Integration College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen518060 China Key Lab. of Adv. Optical Precision Manufacturing Technology of Guangdong Higher Education Institutes Shenzhen Technology University Shenzhen518118 China Han s Laser Technology Industry Group Co. Ltd Shenzhen518057 China

ISBN: (纸本)9781510677661

Mid-infrared conventional solitons and soliton molecules are generated in a polarization-maintaining erbium-doped fluoride fiber oscillator, where a semiconductor saturable absorber is used as the mode locker and a polarization beam splitter is employed for getting linearly polarized output pulses. By rotating the half-wave plate in front of the polarization beam splitter to change the output coupling ratio, the system is switchable between conventional solitons and soliton molecules. conventional solitons with a pulse duration of 120 ps, a maximum average power of 248 mW, and a repetition rate of 44.5 MHz are obtained when the oscillator operates in the single-pulse mode-locked state. By decreasing the output coupling ratio, the operating regime of the oscillator switches to the soliton-molecule mode-locked state, in which soliton-triplets equally distributed at a repetition rate of 44.5 MHz with a signal-to-noise ratio of 78 dB and a temporal separation of 60 ps are obtained. Our work offers a scheme to realize switchable operations between the conventional soliton and the soliton molecule in the mid-infrared polarization-maintaining mode-locked fiber laser. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Fluorine compounds

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：