检索结果-内蒙古大学图书馆

OCRBench: on the hidden mystery of OCR in large multimodal models

science China(Information sciences) 2024年第12期67卷 23-35页

作者： Yuliang LIU Zhang LI Mingxin HUANG Biao YANG Wenwen YU Chunyuan LI Xu-Cheng YIN Cheng-Lin LIU Lianwen JIN Xiang BAI School of Artificial Intelligence and Automation Huazhong University of Science and Technology School of Electronic and Information Engineering South China University of Technology Microsoft Research School of Computer & Communication Engineering University of Science and Technology Beijing Institute of Automation Chinese Academy of Sciences School of Software Engineering Huazhong University of Science and Technology

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of large multimodal models, such as GPT4V and Gemini, in various text-related visual tasks including text recognition, scene text-centric visual question answering(VQA), document-oriented VQA, key information extraction(KIE), and handwritten mathematical expression recognition(HMER). To facilitate the assessment of optical character recognition(OCR) capabilities in large multimodal models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression *** importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal *** evaluation pipeline and benchmark are available at https://***/Yuliang-Liu/Multimodal OCR.

关键词： large multimodal model OCR text recognition scene text-centric VQA document-oriented VQA key information extraction handwritten mathematical expression recognition

来源：评论

学校读者我要写书评

暂无评论

Finite-time PID control for nonlinear nonaffine systems

引用

science China(Information sciences) 2024年第11期67卷 238-251页

作者： Zhiqing LIU Ronghu CHI Biao HUANG Zhongsheng HOU College of Mathematics and Physics Qingdao University of Science and Technology College of Automation and Electronic Engineering Qingdao University of Science and Technology Department of Chemical and Materials Engineering University of Alberta School of Automation Qingdao University

This article proposes a finite-time proportional-integral-derivative(FT-PID) control method to fast stabilize the control system to achieve the desired performance within the predesignated time *** a considered nonaffined nonlinear system, we develop a new dynamic linearization approach to reformulate the system model as a linear data model(LDM) whose arguments are consistent with that used in the PID control law. Then, a projection algorithm is presented to estimate the unknown pseudo gradient vector of the LDM. Subsequently, an adaptive tuning algorithm is designed to update the three PID parameters by solving linear matrix inequalities in terms of the predesignated error precision and the finite-time instant. The finite-time convergence of the proposed FT-PID control system is shown mathematically, which guarantees a pre-specified error precision to be achieved within the predesignated finite-time instants. As a result, not only can the proposed FT-PID control save the control cost but it also improves the production efficiency. The simulation study verifies the results.

关键词： PID control finite-time control nonlinear nonaffine systems linear data model finite-time convergence

来源：评论

学校读者我要写书评

暂无评论

Asymptotical event-based input-output constrained boundary control of flexible manipulator agents under a signed digraph

引用

science China(Information sciences) 2025年第4期68卷 319-335页

作者： Xiangqian YAO Xiangmin XU Wei HE Yu LIU School of Future Technology South China University of Technology School of Automation and Institute of Artificial Intelligence Beijing Information Science and Technology University School of Intelligence Science and Technology University of Science and Technology Beijing School of Automation Science and Engineering South China University of Technology

This article tackles the boundary event-based bipartite consensus tracking control problem for the flexible manipulator multi-agent network over a signed diagraph. Each follower agent is the flexible manipulator with unknown disturbances,modeling uncertainties, input saturations and backlashes, and asymmetric output constraints. To reduce the continuous updating of control inputs, a new dynamic event-triggering mechanism is used. Under multiple constraints, achieving the asymptotic convergence point by point in space of the manipulator's vibration state is a control challenge. To solve this issue, we propose a new asymptotic convergence lemma. In control design, radial basis neural networks are employed to estimate nonlinear uncertain terms and the barrier Lyapunov function is used to accomplish the output constraints. Based on the Lyapunov direct method, a novel distributed boundary event-based control algorithm is designed to guarantee that the closed-loop network can reach the asymptotical bipartite consensus tracking and vibration suppression. Moreover, Zeno behaviors can be excluded for each agent. Finally, some numerical results are presented to demonstrate the validity and superiority of the designed control algorithm.

关键词： flexible-link manipulator input-output constraint event-based asymptotical bipartite tracking vibrationprotectłinebreak control

来源：评论

学校读者我要写书评

暂无评论

Event-based nonsingular fixed-time containment control for nonlinear multiagent systems with dynamic uncertainties

引用

science China(Information sciences) 2025年第5期68卷 413-414页

作者： Yuanbo SU Qihe SHAN Tieshan LI C.L.Philip CHEN Navigation College Dalian Maritime University School of Automation Engineering University of Electronic Science and Technology of China School of Computer Science and Engineering South China University of Technology

Owing to the extensive applications in many areas such as networked systems,formation flying of unmanned air vehicles,and coordinated manipulation of multiple robots,the distributed containment control for nonlinear multiagent systems (MASs) has received considerable attention,for example [1,2].Although the valued studies in [1,2] investigate containment control problems for MASs subject to nonlinearities,the proposed distributed nonlinear protocols only achieve the asymptotic *** a crucial performance indicator for distributed containment control of MASs,the fast convergence is conducive to achieving better control accuracy [3].The work in [4] first addresses the backstepping-based adaptive fuzzy fixed-time containment tracking problem for nonlinear high-order MASs with unknown external ***,the designed fixedtime control protocol [4] cannot escape the singularity problem in the backstepping-based adaptive control *** is well known,the singularity problem has become an inherent problem in the adaptive fixed-time control design,which may cause the unbounded control inputs and even the instability of controlled ***,how to solve the nonsingular fixed-time containment control problem for nonlinear MASs is still open and awaits breakthrough to the best of our knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimization methods rooted in optimal control

引用

science China(Information sciences) 2024年第12期67卷 272-280页

作者： Huanshui ZHANG Hongxia WANG Yeming XU Ziyuan GUO School of Electrical and Automation Engineering Shandong University of Science and Technology School of Control Science and Engineering Shandong University

In the paper, we investigate the optimization problem(OP) by applying the optimal control method. The optimization problem is reformulated as an optimal control problem(OCP) where the controller(iteration updating) is designed to minimize the sum of costs in the future time instant, which thus theoretically generates the “optimal algorithm”(fastest and most stable). By adopting the maximum principle and linearization with Taylor expansion, new algorithms are proposed. It is shown that the proposed algorithms have a superlinear convergence rate and thus converge more rapidly than the gradient descent;meanwhile, they are superior to Newton's method because they are not divergent in general and can be applied in the case of a singular or indefinite Hessian matrix. More importantly, the OCP method contains the gradient descent and the Newton's method as special cases, which discovers the theoretical basis of gradient descent and Newton's method and reveals how far these algorithms are from the optimal algorithm. The merits of the proposed optimization algorithm are illustrated by numerical experiments.

关键词： optimal control optimization methods optimization algorithm maximum principle superlinear convergence

来源：评论

学校读者我要写书评

暂无评论

The optimal control theory——a scientific approach to fundamentally solving control problems

引用

science China(Information sciences) 2025年第1期68卷 389-391页

作者： Huanshui ZHANG School of Electrical and Automation Engineering Shandong University of Science and Technology School of Control Science and Engineering Shandong University

The maximum principle has bridged mathematical optimization to optimal control,ushering in significant developments and refinements in optimal control theory,notably during the 1960s with the advent of linear quadratic (LQ)control and linear quadratic estimation (LQE).This progression propelled optimal control theory into further advancements,encompassing stochastic control,robust/H-infinity control,model predictive control (MPC),networked control,and reinforcement learning *** control,established upon a rigorous mathematical foundation,extends static optimization theory to dynamic systems,exhibiting scientific essence,unity,and ***,since its inception,optimal control theory has served as an indispensable core role across all control-related domains,including communication-constrained control in networked systems,consensus control,cooperative control,and reinforcement learning control.

关键词： control optimal approach fundamentally problems scientific solving theory

来源：评论

学校读者我要写书评

暂无评论

Deterministic learning-based neural output-feedback control for a class of nonlinear sampled-data systems

引用

science China(Information sciences) 2024年第9期67卷 164-183页

作者： Yu ZENG Fukai ZHANG Tianrui CHEN Cong WANG School of Automation Science and Engineering South China University of Technology School of Control Science and Engineering Shandong University

This study investigates the deterministic learning(DL)-based output-feedback neural control for a class of nonlinear sampled-data systems with prescribed performance(PP). Specifically, first, a sampleddata observer is employed to estimate the unavailable system states for the Euler discretization model of the transformed system dynamics. Then, based on the observations and backstepping method, a discrete neural network(NN) controller is constructed to ensure system stability and achieve the desired tracking performance. The noncausal problem encountered during the controller deduction process is resolved using a command filter. Moreover, the regression characteristics of the NN input signals are demonstrated with the observed states. This ensures that the radial basis function NN, based on DL theory, meets the partial persistent excitation condition. Subsequently, a class of discrete linear time-varying systems is proven to be exponentially stable, achieving partial convergence of neural weights to their optimal/actual values. Consequently, accurate modeling of unknown closed-loop dynamics is achieved along the system trajectory from the output-feedback control. Finally, a knowledge-based controller is developed using the modeling *** controller not only enhances the control performance but also ensures the PP of the tracking error. The effectiveness of the scheme is illustrated through simulation results.

关键词： deterministic learning neural networks adaptive neural control predefined performance nonlinear sampled-data systems

来源：评论

学校读者我要写书评

暂无评论

Mean-square prescribed finite-time output consensus of high-order linear multi-agent systems

引用

science China(Information sciences) 2024年第12期67卷 325-326页

作者： Qingpeng LIANG Deqing HUANG Lei MA Jiangping HU Yanzhi WU School of Information Science and Technology Southwest Jiaotong University School of Electrical Engineering Southwest Jiaotong University School of Automation Engineering University of Electronic Science and Technology of China

This study addresses a mean-square prescribed finite-time output consensus problem of high-order linear multi-agent systems with communication noises and thus further generalizes the results in [1–4]. The main contributions include three aspects:(i) It is challenging to analyze and display the finite-time stability due to the presence of communication noises in the sign function and the absence of communication noises in the quadratic Lyapunov function.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Observer-Based Finite-Time Fault Tolerant Control for Non-Strict Feedback Systems

引用

Journal of Systems science & Complexity 2024年第4期37卷 1526-1544页

作者： SHENG Ning LIU Yang CHI Ronghu AI Zidong College of Automation and Electronic Engineering Qingdao University of Science and TechnologyQingdao 266042China

This paper considers the adaptive finite-time control and observer design method for a class of non-strict feedback systems with unmeasurable states,unknown nonlinear dynamics and actuator *** this paper,an observer is proposed to estimate the unmeasurable states in finite-time based on adaptive technique and neural networks,while the actuator faults are not *** filter is used to solve the computational explosion and singularity problems caused by the traditional backstepping and non-strict feedback structure,*** the fault efficiency indicators in real systems are not available,two-layer neural networks are adopted,where the first network is to estimate the unknown nonlinearities of systems and the second one is to estimate fault efficiency indicators and unknown nonlinear *** proposed scheme guarantees that states are bounded through stability ***,two experiments including a numerical example and a spring-mass-damper system are given to verify the effectiveness of the proposed method.

关键词： Command filter fault tolerant control finite-time control non-strict systems two-layer neural networks

来源：评论

学校读者我要写书评

暂无评论

Autonomous embodied navigation task generation from natural language dialogues

引用

science China(Information sciences) 2025年第5期68卷 119-132页

作者： Haifeng XU Yongchang LI Lumeng MA Chunwen LI Yanzhi DONG Xiaohu YUAN Huaping LIU Department of Automation Tsinghua University School of Physics and Electronic Information Yantai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Department of Computer Science and Technology Tsinghua University

Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks often require multiple instructions and prolonged monitoring, which can be time-consuming and demanding for users. Despite this, there is limited research on enabling robots to autonomously generate tasks based on real-life scenarios. Advanced intelligence necessitates robots to autonomously observe and analyze their environment and then generate tasks autonomously to fulfill human requirements without explicit commands. To address this gap, we propose the autonomous generation of navigation tasks using natural language dialogues. Specifically, a robot autonomously generates tasks by analyzing dialogues involving multiple persons in a real office environment to facilitate the completion of item transportation between various *** propose the leveraging of a large language model(LLM) through chain-of-thought prompting to generate a navigation sequence for a robot from dialogues. We also construct a benchmark dataset consisting of 625 multiperson dialogues using the generation capability of LLMs. Evaluation results and real-world experiments in an office building demonstrate the effectiveness of the proposed method.

关键词： proactive robot robot navigation service robot large language model

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：