检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Shen, Jiangrong Xu, Qi Pan, Gang Chen, Badong Faculty of Electronic and Information Engineering Xi’an Jiaotong University China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China State Key Lab of Brain-Machine Intelligence Zhejiang University China National Key Lab of Human-Machine Hybrid Augmented Intelligence Xi’an Jiaotong University China School of Computer Science Dalian University of Technology China

The human brain utilizes spikes for information transmission and dynamically reorganizes its network structure to boost energy efficiency and cognitive capabilities throughout its lifespan. Drawing inspiration from this spike-based computation, Spiking Neural Networks (SNNs) have been developed to construct event-driven models that emulate this efficiency. Despite these advances, deep SNNs continue to suffer from over-parameterization during training and inference, a stark contrast to the brain’s ability to self-organize. Furthermore, existing sparse SNNs are challenged by maintaining optimal pruning levels due to a static pruning ratio, resulting in either under or over-pruning. In this paper, we propose a novel two-stage dynamic structure learning approach for deep SNNs, aimed at maintaining effective sparse training from scratch while optimizing compression efficiency. The first stage evaluates the compressibility of existing sparse subnetworks within SNNs using the PQ index, which facilitates an adaptive determination of the rewiring ratio for synaptic connections based on data compression insights. In the second stage, this rewiring ratio critically informs the dynamic synaptic connection rewiring process, including both pruning and regrowth. This approach significantly improves the exploration of sparse structures training in deep SNNs, adapting sparsity dynamically from the point view of compression efficiency. Our experiments demonstrate that this sparse training approach not only aligns with the performance of current deep SNNs models but also significantly improves the efficiency of compressing sparse SNNs. Crucially, it preserves the advantages of initiating training with sparse models and offers a promising solution for implementing Edge AI on neuromorphic hardware. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optical Evanescent Field for Direct Observation of Sub-100nm Particle Motion on Glass Surface

Optical Evanescent Field for Direct Observation of Sub-100nm...

引用

robotics, Engineering, science, and Technology (RESTCON), International Conference on

作者： Panart Khajornrungruang Thitipat Permpatdechakul Keisuke Suzuki Aran Blattler Yutaka Terayama Daiki Goto Pipat Phaisalpanumas Natthaphon Bun-Athuek Amornphun Phunopas Dept. of Intelligent and Control System Faculty of Computer Science and Systems Engineering Mechanical Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Interdisciplinary Informatics Graduate School of Computer Science and Systems Engineering Mechanical Information Science and Technology Division Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Production and Robotics Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Intelligent and Control System Graduate School of Computer Science and Systems Engineering Mechanical Science and Technology Course Kyushu Institute of Technology Iizuka-Shi Fukuoka Japan Dept. of Industiral Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand Dept. of Mechanical Engineering Technology College of Industrial Technology King Mongkut’s University of Technology North Bangkok Bangsue Bangkok Thailand

To directly investigate the dynamic nanoscale phenomenon on the surface being processed in wet conditions such as precision polishing, and cleaning in semiconductor industrial, an optical method for visualization and observation of each sub-100 nm sized particle that is moving on an interface such as a silica glass surface by applying an evanescent field have been proposing. Subsequently, we developed an experimental apparatus equipped with an optical microscopy system for verifying the moving particle observation method in a laboratory scale. This article introduces some experimentally direct observation results of duplicated wet processes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on spiral winding swimming motion control of a slender legless creature model

引用

High Technology Letters 2021年第4期27卷 415-421页

作者： Lu Zhenli Ma Zhipeng Marko Pencic Maja Cavic Borovac Branislav Roumiana Ilieva Bojan Nemec Marjan Mernik School of Electrical Engineering and Automation Changshu Institute of TechnologyChangshu 215500P.R.China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116P.R.China Faculty of Technical Sciences University of Novi SadNovi Sad 621000Serbia Faculty of Management Technical University of SofiaSofia 1000Bulgaria Department of Automatics Biocybernetics and RoboticsJožef Stefan InstituteLjubljana 1000Slovenia Faculty of Electrical Engineering and Computer Science University of MariborMaribor 462000Slovenia

Through the observation and analysis of the motion trajectory of spiral winding motion for slender legless biological creatures in water,V-REP software is adopted to build a dynamic simulator to study on the mechanism of spiral winding swimming(SWS)*** using the output of spiral function(SF),the dynamic simulation model of slender legless creature(SLC)realizes the SWS motion in *** corresponding experiments under the control of different bending angle of SF to control the dynamic model are also carried out to analyze the water performance of SWS in still *** with the output of two different bending angles of the spiral function,the dynamic model can be used to realize SWS and up/down *** work provides technical reserve and experimental platform for the corresponding study in related fields.

关键词： V-REP spiral winding swimming(SWS) motion control slender legless creature(SLC)

来源：评论

学校读者我要写书评

暂无评论

Terrain Adaption Controller for a Walking Excavator Robot using Deep Reinforcement Learning

Terrain Adaption Controller for a Walking Excavator Robot us...

引用

International Conference on Advanced robotics (ICAR)

作者： Ajish Babu Frank Kirchner DFKI GmbH (German Research Center for Artificial Intelligence) Robotics Innovation Center Bremen Germany Faculty of Mathematics and Computer Science University of Bremen Robotics Group Bremen Germany

ISBN: (纸本)9781665436854

Automation of heavy-duty vehicles using technologies developed in the robotics domain is gaining popularity. One such vehicle is the walking excavator with active suspension chassis for adapting to uneven terrain. The terrain adaption controller automates the suspension control by considering the factors stability, underlying terrain structure, wheel-ground distance, chassis-ground distance, etc. This work builds the controller, which actuates the joints that control the height of the wheels. Deep reinforcement learning is used, considering the complexity of the problem and transferability to other robots. The controller is learned and evaluated in simulation, where continuous terrain with varying slopes is automatically generated. Autoencoders compress the height-map and convert it into latent space of different sizes. Three groups of controllers are then designed based on observations given to the controller. Evaluation of controllers shows that the controllers with ground distances as observation perform better. If the ground distances are part of the observation, there is no significant difference in performance between controllers with different latent space sizes. For controllers with terrain information and no ground distances, the evaluation results match the terrain reconstruction accuracy of the corresponding autoencoder.

关键词： Legged locomotion Suspensions (mechanical systems) Wheels Reinforcement learning Aerospace electronics Manipulators Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Position control of humanoid thorax based on fuzzy PID controller

Position control of humanoid thorax based on fuzzy PID contr...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Siyuan Fang Zaojun Fang Chengbin Peng Chi Zhang Guiling Yang Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo Institute of Materials & Technology Engineering Chinese & Academy of Sciences Ningbo China Ningbo Institute of Materials & Technology Engineering Chinese & Academy of Sciences Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo China College of Science & Technology Ningbo University Ningbo China

Respiration is the most notable vital sign of humans so that it is usually employed to diagnose disease in medicine. Recently, a solution is proposed to decrease the cost of healthcare using flexible stretchable sensors to monitor respiration. However, the sensor is difficult to test millions of cycles on a real human body, which is essential to ensure accuracy and repeatability in practical applications. In this paper, a new humanoid thoracic cavity that mimics rib expansion/constriction is exhibited. Then, a position control based on Fuzzy PID method is presented. Focused on the scenario, the performance between the common PID method and the Fuzzy PID method is investigated. Firstly, the position control based on the Fuzzy PID method is constructed by utilizing position output error and its rate. Then, three gain parameters of PID are adjusted online according to the established fuzzy rules. Finally, the above two methods are compared by simulation and experiments. In a simulation, the fuzzy PID control algorithm improves the response speed, shortens the adjustment time, and meets the requirements of the system for high response and high accuracy. Besides, an experiment is carried out on a humanoid chest prototype. the results show that the control period of the presented method is shortened by about 50% v.s. the traditional PID under the step signal input. Tracking marked points using a laser tracker, the maximum tracking error is 0.0523 mm, the minimum error is 0.0450 mm, and the average error is 0.0473mm. Therefore, the presented method is validated to improve the performance of the humanoid chest.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BSH-Det3D: Improving 3D Object Detection with BEV Shape Heatmap

BSH-Det3D: Improving 3D Object Detection with BEV Shape Heat...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： You Shen Yunzhou Zhang Yanmin Wu Zhenyu Wang Linghao Yang Sonya Coleman Dermot Kerr College of Information Science and Engineering Northeastern University Shenyang China School of Electronic and Computer Engineering Peking University Shenzhen China Department of Electronic and Computer Engineering Faculty of Robotics and Engineering North-eastern University Technical University in Munich Germany Shenyang China Department of Electronic and Computer Engineering Technical University Munich Germany School of Computing Engineering and Intelligent Systems Ulster University N. Ireland UK

The progress of LiDAR-based 3D object detection has significantly enhanced developments in autonomous driving and robotics. However, due to the limitations of LiDAR sensors, object shapes suffer from deterioration in occluded and distant areas, which creates a fundamental challenge to 3D perception. Existing methods estimate specific 3D shapes and achieve remarkable performance. However, these methods rely on extensive computation and memory, causing imbalances between accuracy and real-time performance. To tackle this challenge, we propose a novel LiDAR-based 3D object detection model named BSH-Det3D, which applies an effective way to enhance spatial features by estimating complete shapes from a bird's eye view (BEV). Specifically, we design the Pillar-based Shape Completion (PSC) module to predict the probability of occupancy whether a pillar contains object shapes. The PSC module generates a BEV shape heatmap for each scene. After integrating with heatmaps, BSH-Det3D can provide additional information in shape deterioration areas and generate high-quality 3D proposals. We also design an attention-based densification fusion module (ADF) to adaptively associate the sparse features with heatmaps and raw points. The ADF module integrates the advantages of points and shapes knowledge with negligible overheads. Extensive experiments on the KITTI benchmark achieve state-of-the-art (SOTA) performance in terms of accuracy and speed, demonstrating the efficiency and flexibility of BSH-Det3D. The source code is available on https://***/mystorm16/BSH-Det3D.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SIMUL: Synchronized IMU Dataset of Walking People at Six Body Locations

SIMUL: Synchronized IMU Dataset of Walking People at Six Bod...

引用

International Conference on Indoor Positioning and Indoor Navigation (IPIN)

作者： Steffen Kastner Markus Ebner Markus Bullmann Toni Fetzer Frank Deinzer Marcin Grzegorzek Center for Artificial Intelligence and Robotics Technical University of Applied Sciences Würzburg-Schweinfurt Würzburg Germany Faculty of Computer Science Technical University of Applied Sciences Würzburg-Schweinfurt Würzburg Germany Institute of Medical Informatics University of Lübeck Lübeck Germany

This work presents SIMUL, a new dataset consisting of 550 minutes of annotated motion data from six synchronized IMUs placed consistently at the same strategically chosen positions on the bodies of 32 participants. With a focus on indoor localization, the selection fell on hand, feet, and trouser pockets. Due to the sensor’s synchronization, this selection allows, for example, to label the data recorded in the hand based on the data captured at the feet. For a better generalizability, the dataset was recorded freestyle under many different environmental conditions and walking speeds. Thus, indoors, numerous floor coverings such as stone, wood, carpet and PVC, as well as stairs are included in the data. The outdoor recordings additionally contain uneven surfaces such as paving stones and slopes. The annotation of the participant’s currently performed activity additionally allows this dataset to be used for activity recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on hybrid flow-shop scheduling based on improved genetic algorithm

Research on hybrid flow-shop scheduling based on improved ge...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Haopeng Chen Zaojun Fang Caiming Zhong Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo Institute of Materials & Technology Engineering Chinese & Academy of Sciences Ningbo China Ningbo Institute of Materials & Technology Engineering Chinese & Academy of Sciences Zhejiang Key Laboratory of Robotics and Intelligent Manufacturing Equipment Technology Ningbo China College of Science & Technology Ningbo University Ningbo China

Aiming at the scheduling problem in the production process of hybrid flow-shop, a hybrid flow-shop scheduling model with the objective of minimizing the makespan is established, and a neighborhood search adaptive genetic algorithm (NSAGA) based on heuristic decoding strategy is proposed. An encoding strategy based on the first stage processing sequence and a decoding strategy based on a heuristic rule are used to guide the algorithm to find the optimal solution quickly. In order to speed up the convergence of the algorithm, the elitism strategy is introduced into the genetic operation, and adaptive crossover and mutation strategy based on sigmoid function is designed. In order to enhance the local search capability of the algorithm, a neighborhood search strategy is designed. Finally, the effectiveness and superiority of NSAGA for solving the hybrid flow-shop scheduling problem (HFSP) with different scales are verified by simulation experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Programming Framework for Optimal Planning of Redundant Robots Along Prescribed Paths With Kineto-Dynamic Constraints

arXiv

引用

arXiv 2022年

作者： Ferrentino, Enrico Savino, Heitor J. Franchi, Antonio Chiacchio, Pasquale University of Salerno SA Fisciano84084 Italy Ambev Robotics Lab Anheuser-Busch InBev SP Jacareí12334-480 Brazil The Robotics and Mechatronics Laboratory Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede7522NH Netherlands The Department of Computer Control and Management Engineering Sapienza University of Rome Rome00185 Italy

Offline optimal planning of trajectories for redundant robots along prescribed task space paths is usually broken down into two consecutive processes: first, the task space path is inverted to obtain a joint space path, then, the latter is parametrized with a time law. If the two processes are separated, they cannot optimize the same objective function, ultimately providing sub-optimal results. In this paper, a unified approach is presented where dynamic programming is the underlying optimization technique. Its flexibility allows accommodating arbitrary constraints and objective functions, thus providing a generic framework for optimal planning of real systems. To demonstrate its applicability to a real world scenario, the framework is instantiated for time-optimality on Franka Emika's Panda robot. The well-known issues associated with the execution of non-smooth trajectories on a real controller are partially addressed at planning level, through the enforcement of constraints, and partially through post-processing of the optimal solution. The experiments show that the proposed framework is able to effectively exploit kinematic redundancy to optimize the performance index defined at planning level and generate feasible trajectories that can be executed on real hardware with satisfactory results. Note to Practitioners-The common planning algorithms which consolidated over the years for generating trajectories for non-redundant robots are not adequate to fully exploit the more advanced capabilities offered by redundant robots. This is especially true in performance-demanding tasks, as for robots employed on assembly lines in manufacturing industries, repeatedly performing the same activity. Once the assembly line engineer has defined the tool path in the task space, our planning algorithm unifies inverse kinematics and time parametrization so as to bring the manipulator at its physical limits to achieve specific efficiency goals, being execution time the most typical

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Offline Content-based Recommendation System for Wikimedia Commons Contents

引用

Procedia computer science 2025年 257卷 485-494页

作者： Ahidjo Maitaigahasse Jean Louis Kedieng Ebongue Fendji Marcellin Atemkeng Department Mathematics and Computer Science Faculty of Science University of Ngaoundere 454 Ngaoundere Cameroon Centre for Research Experimentation and Production School of Chemical Engineering and Mineral Industries University of Ngaoundere 454 Ngaoundere Cameroon Stellenbosch Institute for Advanced Study (STIAS) Wallenberg Research Centre at Stellenbosch University Stellenbosch South Africa Department of Robotics and Industrial Informatics School of Chemical Engineering and Mineral Industries University of Ngaoundere 454 Ngaoundere Cameroon Department of Mathematics Rhodes University P.O. Box 6140 Grahamstown South Africa

Recommendation systems are essential for enhancing digital experiences, but their reliance on internet connectivity limits accessibility in regions with limited or no access. This paper presents an offline content-based recommendation system designed to operate without internet dependency by leveraging precomputed Term Frequency-Inverse Document Frequency (TF-IDF) vectors and cosine similarity. To optimize offline performance, we store a locally computed TF-IDF matrix, allowing efficient retrieval of relevant media items through matrix multiplication instead of real-time computation. The system is evaluated using twenty simulated personas representing diverse user interests, demonstrating its ability to generate personalized relevant recommendations. By eliminating the need for online data access, our system makes educational content from Wikimedia Commons accessible in remote areas, schools, and offline learning environments. These findings highlight the potential of offline recommendation systems in bridging the digital divide and providing equitable access to personalized learning resources.

关键词： Content-based recommendation system Wikimedia commons TF-IDF Cosine Similarity

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：