检索结果-内蒙古大学图书馆

Some research works in the state key laboratory of intelligent technology and systems

Frontiers of Electrical and Electronic Engineering in China 2012年第2期7卷 197-199页

作者： Jun ZHU Bo ZHANG State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and TechnologyDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China

This special issue is organized to introduce the research works that have being conducted in the state key laboratory of intelligent technology and systems （LITS）, a state key lab located in Tsinghua University. However, due to space limit, our introduction is certainly not exhaustive. We will use a few sample papers from various research groups to organize this issue.

关键词： the state key laboratory intelligent technology and systems

来源：评论

学校读者我要写书评

暂无评论

Automatic Control of Magnetic Helical Microrobots Docking with Target Objects in Liquid Environments

引用

Journal of Bionic Engineering 2025年第2期22卷 574-584页

作者： Fu Zhao Haoran Rong Lefeng Wang State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin150080China Key Laboratory of Advanced Manufacturing and Intelligent Technology Ministry of EducationHarbin University of Science and TechnologyHarbin150080China

Bio-inspired magnetic helical microrobots have great potential for biomedical and micromanipulation applications. Precise interaction with objects in liquid environments is an important prerequisite and challenge for helical microrobots to perform various tasks. In this study, an automatic control method is proposed to realize the axial docking of helical microrobots with arbitrarily placed cylindrical objects in liquid environments. The docking process is divided into ascent, approach, alignment, and insertion stages. First, a 3D docking path is planned according to the positions and orientations of the microrobot and the target object. Second, a steering-based 3D path-following controller guides the helical microrobot to rise away from the container bottom and approach the target along the path. Third, based on path design with gravity compensation and steering output limits, alignment of position and orientation can be accomplished simultaneously. Finally, the helical microrobot completes the docking under the rotating magnetic field along the target orientation. Experiments verified the automatic docking of the helical microrobot with static targets, including connecting with micro-shafts and inserting into micro-tubes. The object grasping of a reconfigurable helical microrobot aided by 3D automatic docking was also demonstrated. This method enables precise docking of helical microrobots with objects, which might be used for capture and sampling, in vivo navigation control, and functional assembly of microrobots.

关键词： Magnetic actuation Helical microrobots Visual servo Motion control Docking

来源：评论

学校读者我要写书评

暂无评论

Characteristic model-based control of aerial manipulator for improved interaction stability

引用

Science China(Technological Sciences) 2025年第4期68卷 166-178页

作者： Bingkai XIU Zhan LI Yipeng YANG Huijun GAO Research Institute of Intelligent Control and Systems Harbin Institute of TechnologyHarbin150001China State Key Laboratory of Robotics and Systems(HIT) Harbin Institute of TechnologyHarbin150001China

Maintaining contact stability is crucial when the aerial manipulator interacts with the surrounding environment. In this paper, a novel output feedback framework based on a characteristic model is proposed to improve the contact stability of the aerial manipulator. First, only position measurements of the aerial manipulator are introduced to design the practical finite-time command filter-based force observer. Second, an attitude control architecture including characteristic modeling and controller design is presented. In the modeling part, input-output data is utilized to build the characteristic model with fewer parameters and a simpler structure than the traditional dynamic model. Different from conventional control methods, fewer feedback values,namely only angle information, are required for designing the controller in the controller part. In addition, the convergence of force estimation and the stability of the attitude control system are proved by the Lyapunov analysis. Numerical simulation comparisons are conducted to validate the effectiveness of the attitude controller and force observer. The comparative results demonstrate that the tracking error of x and θ channels decreases at least 10.62% and 10.53% under disturbances and the force estimation precision increases at least 45.19% in the different environmental stiffness. Finally, physical flight experiments are conducted to validate the effectiveness of the proposed framework by a self-built aerial manipulator platform.

关键词： aerial manipulator interaction stability contact force observer characteristic model

来源：评论

学校读者我要写书评

暂无评论

DistFlow Safe Reinforcement Learning Algorithm for Voltage Magnitude Regulation in Distribution Networks

引用

Journal of Modern Power systems and Clean Energy 2025年第1期13卷 300-311页

作者： Shengren Hou Aihui Fu Edgar Mauricio Salazar Duque Peter Palensky Qixin Chen Pedro P.Vergara IEEE the Intelligent Electrical Power Grids (IEPG) Group Delft University of Technology the Electrical Energy Systems (EES) Group Eindhoven University of Technology the State Key Laboratory of Power Systems Department of Electrical Engineering Tsinghua University

The integration of distributed energy resources(DERs) has escalated the challenge of voltage magnitude regulation in distribution networks. Model-based approaches, which rely on complex sequential mathematical formulations, cannot meet the real-time demand. Deep reinforcement learning(DRL) offers an alternative by utilizing offline training with distribution network simulators and then executing online without computation. However, DRL algorithms fail to enforce voltage magnitude constraints during training and testing, potentially leading to serious operational violations. To tackle these challenges, we introduce a novel safe-guaranteed reinforcement learning algorithm, the Dist Flow safe reinforcement learning(DF-SRL), designed specifically for real-time voltage magnitude regulation in distribution networks. The DF-SRL algorithm incorporates a Dist Flow linearization to construct an expert-knowledge-based safety layer. Subsequently, the DF-SRL algorithm overlays this safety layer on top of the agent policy, recalibrating unsafe actions to safe domains through a quadratic programming formulation. Simulation results show the DF-SRL algorithm consistently ensures voltage magnitude constraints during training and real-time operation(test) phases, achieving faster convergence and higher performance, which differentiates it apart from(safe) DRL benchmark algorithms.

关键词： Safety Voltage control Distribution networks Regulation Training Vectors Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-based Multi-Objective Scheduling for Distributed Heterogeneous Hybrid Flow Shops with Blocking Constraints

引用

Engineering 2025年第3期46卷 278-291页

作者： Xueyan Sun Weiming Shen Jiaxin Fan Birgit Vogel-Heuser Fandi Bi Chunjiang Zhang State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Institute of Automation and Information Systems Technical University of MunichGarching 85748Germany

This paper investigates a distributed heterogeneous hybrid blocking flow-shop scheduling problem(DHHBFSP)designed to minimize the total tardiness and total energy consumption simultaneously,and proposes an improved proximal policy optimization(IPPO)method to make real-time decisions for the DHHBFSP.A multi-objective Markov decision process is modeled for the DHHBFSP,where the reward function is represented by a vector with dynamic weights instead of the common objectiverelated scalar value.A factory agent(FA)is formulated for each factory to select unscheduled jobs and is trained by the proposed IPPO to improve the decision *** FAs work asynchronously to allocate jobs that arrive randomly at the shop.A two-stage training strategy is introduced in the IPPO,which learns from both single-and dual-policy data for better data *** proposed IPPO is tested on randomly generated instances and compared with variants of the basic proximal policy optimization(PPO),dispatch rules,multi-objective metaheuristics,and multi-agent reinforcement learning *** experimental results suggest that the proposed strategies offer significant improvements to the basic PPO,and the proposed IPPO outperforms the state-of-the-art scheduling methods in both convergence and solution quality.

关键词： Multi-objective Markov decision process Multi-agent deep reinforcement learning Proximal policy optimization Distributed hybrid flow-shop scheduling Blocking constraints

来源：评论

学校读者我要写书评

暂无评论

Beyond Performance of Learning Control Subject to Uncertainties and Noise: A Frequency-Domain Approach Applied to Wafer Stages

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 198-214页

作者： Fazhi Song Ning Cui Shuaiqi Chen Kai Zhang Yang Liu Xinkai Chen Jiubin Tan IEEE the Center of Ultra-precision Optoelectronic Instrument Engineering Harbin Institute of Technology the Key Laboratory of Ultra-Precision Intelligent Instrumentation Ministry of Industry and Information Technology the State Key Laboratory of Precision Electronic Manufacturing Technology and Equipment Guangdong University of Technology the Center of Ultraprecision Optoelectronic Instrument Engineering Harbin Institute of Technology the Key Laboratory of UltraPrecision Intelligent Instrumentation Ministry of Industry and Information Technology the Department of Electronic and Information Systems Shibaura Institute of Technology

The increasingly stringent performance requirement in integrated circuit manufacturing, characterized by smaller feature sizes and higher productivity, necessitates the wafer stage executing a extreme motion with the accuracy in terms of nanometers. This demanding requirement witnesses a widespread application of iterative learning control(ILC), given the repetitive nature of wafer scanning. ILC enables substantial performance improvement by using past measurement data in combination with the system model knowledge. However, challenges arise in cases where the data is contaminated by the stochastic noise, or when the system model exhibits significant uncertainties, constraining the achievable performance. In response to this issue, an extended state observer(ESO) based adaptive ILC approach is proposed in the frequency *** being model-based, it utilizes only a rough system model and then compensates for the resulting model uncertainties using an ESO, thereby achieving high robustness against uncertainties with minimal modeling effort. Additionally, an adaptive learning law is developed to mitigate the limited performance in the presence of stochastic noise, yielding high convergence accuracy yet without compromising convergence speed. Simulation and experimental comparisons with existing model-based and data-driven inversion-based ILC validate the effectiveness as well as the superiority of the proposed method.

关键词： Extended state observer learning control model uncertainties motion control stochastic noise

来源：评论

学校读者我要写书评

暂无评论

An optical carbon nanotube fibre probe for measurement of nano structures with large aspect ratio

引用

Nano Research 2025年第3期18卷 436-443页

作者： Weihao Tao Shuhao Zhao Hanjin Dong Ze Zhang Peirui Ji Shenghan Qin Wenbo Hu Jinlong Zhu Renjie Zhou Shuming Yang State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong UniversityXi’an 710049China State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China Department of Biomedical Engineering The Chinese University of Hong KongHong KongChina

With the development of imaging and measurement technologies,scanning near-field optical microscopy(SNOM)has achieved high signal-to-noise *** resolution of a fibre probe-based SNOM system is capable of reaching 10 ***,SNOM applications are presently constrained to the measurement of near-field optical information to relatively straightforward structures,including quantum dots,carbon nanotubes,graphene,and so *** geometry of conventional fibre probes,with tips at an angle of 30°-60°,presents a challenge for accurately imaging complex surface *** paper proposes a carbon nanotube composite fibre probe(CNT-FP)with a large aspect *** key point is that a carbon nanotube bundle is composited at the tip of conventional surface plasmon polaritons fibre probes(SPPs-FP),which are the fibre probes coated with gold film to excite the *** coupling,propagation,and focusing effects of SPPs on the carbon nanotube bundle are ***-FPs have been fabricated and applied to measure a grating with the depth of 400 nm and the width of 400 *** experimental results show that the measurement accuracy and imaging quality of CNT-FP are nearly one order of magnitude higher than that of conventional SPPs-FP,as evidenced by evaluation criteria such as line roughness and volatility ***,it achieves an optical resolution of 72.1 nm in the measurements of a nano structure with large aspect *** provides an effective solution of measuring structures with larger aspect ratios.

关键词： carbon nanotubes fibre optic probes surface plasmon polaritons nano-focusing large aspect ratio

来源：评论

学校读者我要写书评

暂无评论

A data-driven rolling optimization method for trajectory tracking error prediction of CNC machine tools

引用

Science China(Technological Sciences) 2025年第1期68卷 270-285页

作者： Yinxin GUAN Jixiang YANG Shizhong TAN Han DING School of Mechanical Science and Engineering State Key Laboratory of Intelligent Manufacturing Equipment and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

The dynamic performance of the feed-drive system in CNC machine tools directly influences the accuracy of machined *** enhance the motion control performance of CNC machine tools,a high-precision model of the feed-drive system is ***,current modeling methods for feed-drive systems seldom consider time-varying factors such as loads,wear,and *** a result,the model accuracy degrades when the system characteristics are affected by these time-varying *** this paper,a rolling optimization method with partial weights frozen is developed to realize quick iterative learning of a data-driven model for a feed drive system with time-varying characteristics using a small amount of ***,the long short-term memory fully connected(LSTM-FC)network is built and divided into feature extraction and output fitting parts based on their ***,a weight freezing-based rolling optimization method is *** weights in the feature extraction part are frozen,which preserves the learned common knowledge and patterns by solidifying the way that high-dimensional features are extracted from the *** adjusting the weights in the output fitting part,the extracted highdimensional features are remapped to the new data distribution changed by time-varying ***,the performance of the developed rolling optimization method is confirmed by *** results show that the proposed rolling optimization method reduces the maximum prediction errors by 49.5%and the total training time by 96.3%compared with existing methods,which demonstrates that the proposed method can restore model accuracy when the system characteristics change due to timevarying factors,and significantly accelerate the optimization process by rolling optimization.

关键词： rolling optimization feed-drive system data-driven time-varying machine tool

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Fault-Tolerant Bipartite Consensus Tracking for Multi-Agent systems With a Non-Autonomous Leader

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 279-281页

作者： Yan Zhou Guanghui Wen Jialing Zhou Tao Yang the Department of Systems Science Southeast University the State Key Laboratory of CNS/ATM Beijing Institute of Technology the Beijing Institute of Technology (Zhuhai) the State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

Dear Editor,This letter studies the bipartite consensus tracking problem for heterogeneous multi-agent systems with actuator faults and a leader's unknown time-varying control input. To handle such a problem, the continuous fault-tolerant control protocol via observer design is developed. In addition, it is strictly proved that the multi-agent system driven by the designed controllers can still achieve bipartite consensus tracking after faults occur.

关键词： Time varying control systems

来源：评论

学校读者我要写书评

暂无评论

Self-Organised Sequential Multi-Agent Reinforcement Learning for Closely Cooperation Tasks

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5967-5974页

作者： Fu, Hao You, Mingyu Zhou, Hongjun He, Bin Tongji University College of Electronic and Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems China Shanghai Key Laboratory of Intelligent Autonomous Systems State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems China

Cooperative tasks are common in multi-agent systems, with closely cooperative tasks being a special case of this, where a change in the state of the environment requires multiple agents to perform a specific operation at the same time. Take a box-pushing task as an example, the box is heavy and requires multiple agents to push it simultaneously. Optimal actions in a closely cooperation task are correlated with the actions of other agents, which makes the individual optimal action potentially inconsistent with the group optimal action, which leads to more non-globally optimal Nash equilibrium policies in the problem. This makes it easier for the policy learned by reinforcement learning to fall into these locally optimal policies. In this paper, we propose a self-organised sequential multi-agent reinforcement learning algorithm (SOS-MARL). We propose sequential decision-making to change the optimization objective of the agent's policy so that the learned policy tends to group optimal policies. And propose an automatic grouping mechanism to make the policy smoother for training and reasoning in large-scale agent environments. We decompose the joint action value factorization outside the group into a combination of each group action value, thus guiding the agents to improve their group policies in a fine-grained manner. We deployed scenarios in both simulated and real environments and compared SOS-MARL with various classical MARL algorithms on box-pushing tasks, demonstrating the state-of-the-art of our method. © 2016 IEEE.

关键词： Multi agent systems

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：