检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Fang, Qihang Xiong, Gang Wang, Fang Shen, Zhen Dong, Xisong Wang, Fei-Yue State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350368604

Additive manufacturing (AM) is a promising technology to tailor complex structures in a layer-by-layer fashion. Its wide adoption, however, is hampered by occurrence of defects that deteriorates product quality. Defect detection methods have therefore been developed to address quality issues, primarily utilizing deep learning models. Despite achieving appreciable results, these models require a substantial amount of labeled data and extensive training, which are costly and time-consuming. Thus, it is worth developing a new approach that can perform defect detection (1) with minimal labeled data, and (2) without the necessity for model updating. Recently, the large language model (LLM) has demonstrated remarkable generalization capability across various fields. It features an in-context learning (ICL) capability that allows it to learn from a context without any retraining. This study explores the potential of applying an LLM for AM defect detection based on ICL. To this end, a dataset pertaining to the resin deposition status in vat photopolymerization, as a field where prevailing LLMs have limited exposure, is collected. Two contributions are made to achieve more accurate defect detection by prompting. First, a multimodal context that includes both image-label pairs and expert knowledge is tailored, which contains comprehensive information about deposition status. Second, a repeated query and voting (RQV) technique is proposed to mitigate occasional misjudgements, thus enhancing the reliability of the defect detection. Comprehensive ablation studies verify the effectiveness of both the multimodal context and RQV technique. As a result, 96.2% classification accuracy is achieved in such a challenging few-shot setting, obviating the need of model updating. © 2024 IEEE.

关键词： labeled data

来源：评论

学校读者我要写书评

暂无评论

Real-World Learning control for Autonomous Exploration of a Biomimetic Robotic Shark

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第4期70卷 3966-3974页

作者： Yan, Shuaizheng Wu, Zhengxing Wang, Jian Huang, Yupei Tan, Min Yu, Junzhi Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Coll Engn BIC ESAT State Key Lab Turbulence & Complex SystDept Adv Beijing 100871 Peoples R China

With the development of learning-based autonomous underwater exploration method of robotic fish, how to improve data quality and sampling efficiency, so as to achieve better control performance, becomes a challenging research subject. To address this issue, in this article, a feasible real-world deep reinforcement learning framework for autonomous underwater exploration of robotic fish is proposed, which ably avoids model discrepancy generated in virtual training. The designed framework consists of three phases: 1) teaching initialization;2) regular update of reinforcement learning;and 3) phased consolidation training. Especially, reasonable teaching initialization improves the data sampling efficiency and stabilizes the real-world early training. The consolidation training ensures the reproducibility of good controllers by interim imitation learning in the middle training phase. Extensive underwater experiments on a novel self-developed biomimetic robotic shark show that the proposed real-world learning method significantly improves the safety and efficiency of autonomous exploration based on local sensor information, providing a promising solution for exploring in uncharted wild waters.

关键词： Autonomous exploration deep reinforcement learning (DRL) imitation learning (IL) robotic fish

来源：评论

学校读者我要写书评

暂无评论

Locomotion Optimization of a Tendon-Driven Robotic Fish With Variable Passive Tail Fin

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第5期70卷 4983-4992页

作者： Qiu, Changlin Wu, Zhengxing Wang, Jian Tan, Min Yu, Junzhi Chinese Acad Sci State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex SystBIC ESAT Beijing 100871 Peoples R China

This article explores a set of locomotion optimization methods for a novel tendon-driven robotic fish. With the typical features of the dual tendon driving active tail and variable stiffness passive caudal fin, a fully functioning tendon-drive robotic fish is developed. Next, a practical dynamic model for the tendon-driven robotic fish is established with full consideration of variable stiffness passive caudal fin, and the model parameters are accurately identified via data-driven methods. More importantly, to improve the motion performances, an asymmetric central pattern generator is particularly proposed, and an adjustment rule of passive stiffness is explored to fit different motion states of the robotic fish. Finally, extensive simulations and aquatic experiments verify the feasibility of the proposed prototype and locomotion optimization methods. The obtained results show that the improvements of steering radius and forward swimming velocity are 36.3% and 29%, respectively. At present, our robotic fish can achieve maximum forward swimming as 1.04 BL/s (BL for the body length), maximum turning rate as 153.3 degrees/s, and the minimum turning radius reaches to 0.31 BL, providing a valuable reference for bioinspired research of aquatic mechanical design and locomotion control.

关键词： Robots Tail Springs Sports Wires Service robots Tendons Asymmetric central pattern generator (A-CPG) motion control robotic fish underwater robotics variable passive caudal fin

来源：评论

学校读者我要写书评

暂无评论

Entity Dependency Learning Network With Relation Prediction for Video Visual Relation Detection

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems FOR VIDEO TECHNOLOGY 2024年第12期34卷 12425-12436页

作者： Zhang, Guoguang Tang, Yepeng Zhang, Chunjie Zheng, Xiaolong Zhao, Yao Beijing Jiaotong Univ Sch Comp Sci & Technol Beijing Key Lab Adv Informat Sci & Network Technol Beijing 100044 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100190 Peoples R China

Video Visual Relation Detection (VidVRD) is a pivotal task in the field of video analysis. It involves detecting object trajectories in videos, predicting potential dynamic relation between these trajectories, and ultimately representing these relationships in the form of triplets. Correct prediction of relation is vital for VidVRD. Existing methods mostly adopt the simple fusion of visual and language features of entity trajectories as the feature representation for relation predicates. However, these methods do not take into account the dependency information between the relation predication and the subject and object within the triplet. To address this issue, we propose the entity dependency learning network(EDLN), which can capture the dependency information between relation predicates and subjects, objects, and subject-object pairs. It adaptively integrates these dependency information into the feature representation of relation predicates. Additionally, to effectively model the features of the relation existing between various object entities pairs, in the context encoding phase for relation predicate features, we introduce a fully convolutional encoding approach as a substitute for the self-attention mechanism in the Transformer. Extensive experiments on two public datasets demonstrate the effectiveness of the proposed EDLN.

关键词： Feature extraction Trajectory Visualization Task analysis Object detection Encoding Decoding Visual relation detection entity dependency learning video understanding

来源：评论

学校读者我要写书评

暂无评论

Exploring Latent Transferability of feature components

引用

PATTERN RECOGNITION 2025年 160卷

作者： Wang, Zhengshan Chen, Long He, Juan Yang, Linyao Wang, Fei-Yue Univ Macau Fac Sci & Technol Dept Comp & Informat Sci Macau 999078 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China

Feature disentanglement techniques have been widely employed to extract transferable (domain-invariant) features from non-transferable (domain-specific) features in Unsupervised Domain Adaptation (UDA). However, due to the complex interplay among high-dimensional features, the separated "non-transferable" features may still be partially informative. Suppressing or disregarding them, as commonly employed in previous methods, can overlook the inherent transferability. In this work, we introduce two concepts: Partially Transferable Class Features and Partially Transferable Domain Features (PTCF and PTDF), and propose a succinct feature disentanglement technique. Different with prior works, we do not seek to thoroughly peel off the nontransferable features, as it is challenging practically. Instead, we take the two-stage strategy consisting of rough feature disentanglement and dynamic adjustment. We name our model as ELT because it can systematically Explore Latent Transferability of feature components. ELT can automatically evaluate the transferability of internal feature components, dynamically giving more attention to features with high transferability and less to features with low transferability, effectively solving the problem of negative transfer. Extensive experimental results have proved its efficiency. The code and supplementary file will be available at https://***/ njtjmc/ELT.

关键词： Unsupervised domain adaptation Feature disentanglement Adversarial learning Dynamic learning

来源：评论

学校读者我要写书评

暂无评论

Incremental networked predictive control of multi-agent systems with plant-model mismatch and random communication constraints

引用

IET control THEORY AND APPLICATIONS 2022年第1期16卷 51-65页

作者： Dong, Zhe Zheng, Chang-Bing Pang, Zhong-Hua Sun, Jian North China Univ Technol Key Lab Fieldbus Technol & Automat Beijing Beijing 100144 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Beijing Inst Technol Sch Automat State Key Lab Intelligent Control & Decis Comple Beijing Peoples R China

In this paper, we discuss the cooperative output tracking problem for networked multi-agent systems (NMASs) with plant-model mismatch as well as random communication constraints in the forward and feedback channels of each agent. In order to compensate actively for random communication constraints, that is, network-induced delays and packet dropouts, an incremental networked predictive control scheme based on a state observer is proposed, which consists of a data buffer, an incremental networked predictor, and a network delay compensator. For both the plant-model mismatch case and the plant-model match case, the stability conditions of resulting closed-loop NMASs are derived, respectively. Using the proposed method, the simulation results for three DC motor systems are presented to indicate that desired tracking performance can be achieved.

关键词： Algebra control system analysis and synthesis methods Stability in control theory Optimal control Multivariable control systems Self-adjusting control systems Nonlinear control systems

来源：评论

学校读者我要写书评

暂无评论

Constrained-Cost Adaptive Dynamic Programming for Optimal control of Discrete-Time Nonlinear systems

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING systems 2024年第3期35卷 3251-3264页

作者： Wei, Qinglai Li, Tao Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China

For discrete-time nonlinear systems, this research is concerned with optimal control problems (OCPs) with constrained cost, and a novel value iteration with constrained cost (VICC) method is developed to solve the optimal control law with the constrained cost functions. The VICC method is initialized through a value function constructed by a feasible control law. It is proven that the iterative value function is nonincreasing and converges to the solution of the Bellman equation with constrained cost. The feasibility of the iterative control law is proven. The method to find the initial feasible control law is given. Implementation using neural networks (NNs) is introduced, and the convergence is proven by considering the approximation error. Finally, the property of the present VICC method is shown by two simulation examples.

关键词： Costs Cost function Performance analysis Optimal control Nonlinear systems Dynamic programming Convergence Adaptive dynamic programming (ADP) approximate dynamic programming constrained cost optimal control reinforcement learning value iteration (VI)

来源：评论

学校读者我要写书评

暂无评论

IMTRAC: Image-Based Modeling for Transformative Traffic control via Foundation Models 17

IMTRAC: Image-Based Modeling for Transformative Traffic Cont...

引用

17th IFAC Symposium on control of Transportation systems (CTS)

作者： Dai, Xingyuan Tang, Yiqing Guo, Chao Chen, Yuanyuan Lv, Yisheng Wang, Fei-Yue Chinese Acad Sci State Key Lab Multimodal Artificial Intelligence Inst Automat Beijing 100190 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China

This paper introduces the Image-based Modeling for Transformative Traffic control (IMTRAC) framework, which revolutionizes urban traffic management by integrating image-based representations, foundation models, and dynamic signaling. It transitions from textual to visual data analysis, transforming complex traffic scenes into quantifiable insights. The image-based representation is then analyzed by foundation models to infer refined and effective traffic control policies. Our experimental results show marked improvements in traffic flow and reductions in waiting times, highlighting IMTRAC's ability to outperform traditional control methods. The proposed IMTRAC promises a significant leap towards smarter, efficient urban traffic systems, leveraging the synergy of advanced imaging techniques and multi-modal foundation models to enhance control decisions. Copyright (C) 2024 The Authors. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0/)

关键词： Foundation models Intelligent transportation systems Traffic control

来源：评论

学校读者我要写书评

暂无评论

Computational Experiments for complex Social systems:Experiment Design and Generative Explanation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 1022-1038页

作者： Xiao Xue Deyu Zhou Xiangning Yu Gang Wang Juanjuan Li Xia Xie Lizhen Cui Fei-Yue Wang the School of Computer Software College of Intelligence and ComputingTianjin UniversityTianjin 300350China the School of Software and the Joint SDUNTU Centre for Artificial Intelligence Research(C-FAIR) Shandong UniversityJinan 250101China the Information School Xi’an University of Financial and EconomicsXi’an 710100China the State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Hainan University Haikou 570228China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 1001901China

Powered by advanced information technology,more and more complex systems are exhibiting characteristics of the cyber-physical-social systems(CPSS).In this context,computational experiments method has emerged as a novel approach for the design,analysis,management,control,and integration of CPSS,which can realize the causal analysis of complex systems by means of“algorithmization”of“counterfactuals”.However,because CPSS involve human and social factors(e.g.,autonomy,initiative,and sociality),it is difficult for traditional design of experiment(DOE)methods to achieve the generative explanation of system *** address this challenge,this paper proposes an integrated approach to the design of computational experiments,incorporating three key modules:1)Descriptive module:Determining the influencing factors and response variables of the system by means of the modeling of an artificial society;2)Interpretative module:Selecting factorial experimental design solution to identify the relationship between influencing factors and macro phenomena;3)Predictive module:Building a meta-model that is equivalent to artificial society to explore its operating ***,a case study of crowd-sourcing platforms is presented to illustrate the application process and effectiveness of the proposed approach,which can reveal the social impact of algorithmic behavior on“rider race”.

关键词： Agent-based modeling computational experiments cyber-physical-social systems(CPSS) generative deduction generative experiments meta model

来源：评论

学校读者我要写书评

暂无评论

Adaptive bias-variance trade-off in advantage estimator for actor-critic algorithms

引用

NEURAL NETWORKS 2024年 169卷 764-777页

作者： Chen, Yurou Zhang, Fengyi Liu, Zhiyong Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Chinese Acad Sci Ctr Excellence Brain Sci & Intelligence Technol Shanghai Peoples R China

Actor-critic methods are leading in many challenging continuous control tasks. Advantage estimators, the most common critics in the actor-critic framework, combine state values from bootstrapping value functions and sample returns. Different combinations balance the bias introduced by state values and the variance returned by samples to reduce estimation errors. The bias and variance constantly fluctuate throughout training, leading to different optimal combinations. However, existing advantage estimators usually use fixed combinations that fail to account for the trade-off between minimizing bias and variance to find the optimal estimate. Our previous work on adaptive advantage estimation (AAE) analyzed the sources of bias and variance and offered two indicators. This paper further explores the relationship between the indicators and their optimal combination through typical numerical experiments. These analyses develop a general form of adaptive combinations of state values and sample returns to achieve low estimation errors. Empirical results on simulated robotic locomotion tasks show that our proposed estimators achieve similar or superior performance compared to previous generalized advantage estimators (GAE).

关键词： Reinforcement Learning Policy gradient Actor-critic Value function Bias-variance trade-off

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：