检索结果-内蒙古大学图书馆

Embodied intelligence in RO/RO logistic terminal:autonomous intelligent transportation robot architecture

Science China(Information Sciences) 2025年第5期68卷 153-169页

作者： Yongkang XU Runjiao BAO Lin ZHANG Junzheng WANG Shoukun WANG School of Automation Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology

In this paper, an autonomous intelligent transportation robot equipped with intelligent perception and autonomous planning modules is proposed to meet the requirements of roll-on/roll-off(RO/RO) logistics terminals for the autonomous transportation of various types of finished vehicles. Based on the robot operating system(ROS) framework and a modular design approach, the robot integrates several key components, including a visual perception module, an autonomous planning module, a motion control module, an execution module, and an energy module. First, an improved convex hull algorithm efficiently extracts point cloud data, enhancing the efficiency of point cloud processing and addressing the issue of excessive target data. Three different evaluation methods were employed to determine the optimal bounding box of the target vehicle and to obtain its pose state. Second, improved proximal policy optimization(PPO) and generalized advantage estimation(GAE) algorithms, which are utilized in this paper, were implemented to autonomously plan collisionfree trajectories for robots, facilitating their movement from an initial position to the target transportation location, and subsequently to the final placement position. Finally, physical experiments confirmed that the robot effectively mimics the three fundamental components of humanoid functionality: perception, cognition, and action, thus enabling autonomous and intelligent handling of complex vehicle transportation tasks. These demonstrations validate the feasibility and effectiveness of the proposed robot.

关键词： embodied intelligence transportation robot RO/RO logistic terminal detection autonomous planning

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

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

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

Inexact proximal gradient algorithm with random reshuffling for nonsmooth optimization

引用

Science China(Information Sciences) 2025年第1期68卷 219-237页

作者： Xia JIANG Yanyan FANG Xianlin ZENG Jian SUN Jie CHEN National Key Lab of Autonomous Intelligent Unmanned Systems School of AutomationBeijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center School of Electronic and Information Engineering Tongji University

Proximal gradient algorithms are popularly implemented to achieve convex optimization with nonsmooth regularization. Obtaining the exact solution of the proximal operator for nonsmooth regularization is challenging because errors exist in the computation of the gradient; consequently, the design and application of inexact proximal gradient algorithms have attracted considerable attention from researchers. This paper proposes computationally efficient basic and inexact proximal gradient descent algorithms with random reshuffling. The proposed stochastic algorithms take randomly reshuffled data to perform successive gradient descents and implement only one proximal operator after all data pass through. We prove the convergence results of the proposed proximal gradient algorithms under the sampling-without-replacement reshuffling *** computational errors exist in gradients and proximal operations, the proposed inexact proximal gradient algorithms can converge to an optimal solution neighborhood. Finally, we apply the proposed algorithms to compressed sensing and compare their efficiency with some popular algorithms.

关键词： proximal operator random reshuffling inexact computation compressed sensing nonsmooth optimization

来源：评论

学校读者我要写书评

暂无评论

MC-NeRF: Multi-Camera Neural Radiance Fields for Multi-Camera Image Acquisition systems

引用

IEEE Transactions on Visualization and Computer Graphics 2025年第5期31卷 2725-2735页

作者： Gao, Yu Su, Lutong Liang, Hao Yue, Yufeng Yang, Yi Fu, Mengyin Beijing Institute of Technology School of Automation Beijing China Beijing Institute of Technology National Key Lab of Autonomous Intelligent Unmanned Systems Beijing China

Neural Radiance Fields (NeRF) use multi-view images for 3D scene representation, demonstrating remarkable performance. As one of the primary sources of multi-view images, multi-camera systems encounter challenges such as varying intrinsic parameters and frequent pose changes. Most previous NeRF-based methods assume a unique camera and rarely consider multi-camera scenarios. Besides, some NeRF methods that can optimize intrinsic and extrinsic parameters still remain susceptible to suboptimal solutions when these parameters are poor initialized. In this paper, we propose MC-NeRF, a method for joint optimization of both intrinsic and extrinsic parameters alongside NeRF, allowing individual camera parameters for each image. First, we analyze the coupling issue that arises from the joint optimization between intrinsics and extrinsics, and propose a decoupling constraint utilizing auxiliary images. To further address the degenerate cases in the decoupling process, we introduce an efficient auxiliary image acquisition scheme to mitigate these effects. Furthermore, recognizing that most existing datasets are designed for a unique camera, we provided a new dataset that includes both simulated data and real-world data. Experiments demonstrate the effectiveness of our method in scenarios where each image corresponds to different camera parameters. Specifically, our approach outperforms the baselines favorably in terms of intrinsics estimation, extrinsics estimation, scale estimation, and rendering quality. The Code and supplementary materials are available at https://***/MC-NeRF. © 1995-2012 IEEE.

关键词： Volume rendering

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 improved efficient adaptive method for large-scale multiexplosives explosion simulations

引用

Defence technology(防务技术) 2025年第3期45卷 28-47页

作者： Tao Li Cheng Wang Baojun Shi School of Mechanical Engineering Key Laboratory of Advanced Intelligent Protective Equipment TechnologyMinistry of EducationHebei University of TechnologyTianjin300401China State Key Lab of Explosion Science and Safety Protection Beijing Institute of TechnologyBeijing 100081China

Shock wave caused by a sudden release of high-energy,such as explosion and blast,usually affects a significant range of *** utilization of a uniform fine mesh to capture sharp shock wave and to obtain precise results is inefficient in terms of computational *** is particularly evident when large-scale fluid field simulations are conducted with significant differences in computational domain *** this work,a variable-domain-size adaptive mesh enlargement(vAME)method is developed based on the proposed adaptive mesh enlargement(AME)method for modeling multi-explosives explosion *** vAME method reduces the division of numerous empty areas or unnecessary computational domains by adaptively suspending enlargement operation in one or two directions,rather than in all directions as in AME method.A series of numerical tests via AME and vAME with varying nonintegral enlargement ratios and different mesh numbers are simulated to verify the efficiency and order of *** estimate of speedup ratio is analyzed for further efficiency *** large-scale near-ground explosion experiments with single/multiple explosives are performed to analyze the shock wave superposition formed by the incident wave,reflected wave,and Mach ***,the vAME method is employed to validate the accuracy,as well as to investigate the performance of the fluid field and shock wave propagation,considering explosive quantities ranging from 1 to 5 while maintaining a constant total *** results show a satisfactory correlation between the overpressure versus time curves for experiments and numerical *** vAME method yields a competitive efficiency,increasing the computational speed to 3.0 and approximately 120,000 times in comparison to AME and the fully fine mesh method,*** indicates that the vAME method reduces the computational cost with minimal impact on the results for such large-scale high-energy release problems with signi

关键词： Large-scale explosion Shock wave Adaptive method Fluid field simulations Efficient method

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 Helmet Detection Algorithm Based on Transformers with Deformable Attention Module

引用

Chinese Journal of Electronics 2025年第1期34卷 229-241页

作者： Songle Chen Hongbo Sun Yuxin Wu Lei Shang Xiukai Ruan Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province Nanjing University of Posts and Telecommunications State Key Lab for Novel Software Technology Nanjing University Institute of Intelligent Locks Wenzhou University

Wearing a helmet is one of the effective measures to protect workers' safety. To address the challenges of severe occlusion, multi-scale, and small target issues in helmet detection, this paper proposes a helmet detection algorithm based on deformable attention transformers. The main contributions of this paper are as follows. A compact end-to-end network architecture for safety helmet detection based on transformers is proposed. It cancels the computationally intensive transformer encoder module in the existing detection transformer(DETR) and uses the transformer decoder module directly on the output of feature extraction for query decoding, which effectively improves the efficiency of helmet detection. A novel feature extraction network named Swin transformer with deformable attention module(DSwin transformer) is proposed. By sparse cross-window attention, it enhances the contextual awareness of multi-scale features extracted by Swin transformer, and keeps high computational efficiency simultaneously. The proposed method generates the query reference points and query embeddings based on the joint prediction probabilities, and selects an appropriate number of decoding feature maps and sparse sampling points for query decoding, which further enhance the inference capability and processing speed. On the benchmark safety-helmet-wearing-dataset(SHWD), the proposed method achieves the average detection accuracy mAP@0.5 of 95.4% with 133.35G floating-point operations per second(FLOPs) and 20 frames per second(FPS), the state-of-the-art method for safety helmet detection.

关键词： Head Accuracy Network architecture Benchmark testing Transformers Feature extraction Safety Decoding Computational efficiency Detection algorithms

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：