检索结果-内蒙古大学图书馆

An Improved High Precision 3D Semantic Mapping of Indoor Scenes from RGB-D Images

Computer Modeling in Engineering & Sciences 2023年第12期137卷 2621-2640页

作者： Jing Xin Kenan Du Jiale Feng Mao Shan Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of TechnologyXi’an710048China Australian Centre for Field Robotics The University of SydneySydney2006Australia

This paper proposes an improved high-precision 3D semantic mapping method for indoor scenes using RGB-D *** current semantic mapping algorithms suffer from low semantic annotation accuracy and insufficient real-time *** address these issues,we first adopt the Elastic Fusion algorithm to select key frames from indoor environment image sequences captured by the Kinect sensor and construct the indoor environment space ***,an indoor RGB-D image semantic segmentation network is proposed,which uses multi-scale feature fusion to quickly and accurately obtain object labeling information at the pixel level of the spatial point cloud ***,Bayesian updating is used to conduct incremental semantic label fusion on the established spatial point cloud *** also employ dense conditional random fields(CRF)to optimize the 3D semantic map model,resulting in a high-precision spatial semantic map of indoor *** results show that the proposed semantic mapping system can process image sequences collected by RGB-D sensors in real-time and output accurate semantic segmentation results of indoor scene images and the current local spatial semantic ***,it constructs a globally consistent high-precision indoor scenes 3D semantic map.

关键词： 3D semantic map online reconstruction RGB-D images semantic segmentation indoor mobile robot

来源：评论

学校读者我要写书评

暂无评论

Full Resolution Repetition Counting 16th

Full Resolution Repetition Counting

引用

16th International Conference on Intelligent robotics and Applications, ICIRA 2023

作者： Li, Jianing Chen, Bowen Wang, Zhiyong Liu, Honghai School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819964826

Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive actions, also optimization challenges in end-to-end video model training, down-sampling is commonly utilized in recent state-of-the-art methods, leading to ignorance of several repetitive samples. In this paper, we attempt to understand repetitive actions from a full temporal resolution view, by combining offline feature extraction and temporal convolution networks. The former step enables us to train repetition counting network without down-sampling while preserving all repetitions regardless of the video length and action frequency, and the later network models all frames in a flexible and dynamically expanding temporal receptive field to retrieve all repetitions with a global aspect. Besides, temporal self-similarity matrix is used in our model to represent the correlation of action, which contains much cycle information in time series. We experimentally demonstrate that our method achieves better or comparable performance in three public datasets, i.e., TransRAC, UCFRep and QUVA. We expect this work will encourage our community to think about the importance of full temporal resolution. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Spatial confinement of free-standing graphene sponge enables excellent stability of conversion-type Fe_(2)O_(3)anode for sodium storage

引用

Chinese Chemical Letters 2025年第3期36卷 544-549页

作者： Jun Dong Senyuan Tan Sunbin Yang Yalong Jiang Ruxing Wang Jian Ao Zilun Chen Chaohai Zhang Qinyou An Xiaoxing Zhang Hubei Key Laboratory for High-efficiency Utilization of Solar Energy and Operation Control of Energy Storage System Hubei University of TechnologyWuhan 430068China State Key Laboratory of New Textile Materials and Advanced Processing Technologies Wuhan Textile UniversityWuhan 430200China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Wuhan University of TechnologyWuhan 430070China Nanjing University of Aeronautics and Astronautics Nanjing 210016China

Conversion-type anode materials are highly desirable for Na-ion batteries(NIBs)due to their high theoretical ***,the active materials undergo severe expansion and pulverization during the sodiation,resulting in inferior cycling ***,a self-supporting three-dimensional(3D)graphene sponge decorated with Fe_(2)O_(3)nanocubes(rGO@Fe_(2)O_(3))is ***,the 3D graphene sponge with resilience and high porosity benefits to accommodate the volume expansion of the Fe_(2)O_(3)nanocubes and facilitates the rapid electrons/ions transport,enabling spatial confinement to achieve outstanding ***,the free-standing rGO@Fe_(2)O_(3)can be directly used as an electrode without additional binders and conductive additives,which helps to obtain a higher energy *** on the total mass of the rGO@Fe_(2)O_(3)material,the rGO@Fe_(2)O_(3)anode presents a specific capacity of 859 mAh/g at 0.1 A/*** also delivers an impressive cycling performance(327 mAh/g after 2000 cycles at 1 A/g)and a superior rate capacity(162mAh/g at 20 A/g).The coin-type Na_(3)V_(2)(PO_(4))_(3)@C//rGO@Fe_(2)O_(3)NIB exhibits an energy density of 265.3Wh/*** unique 3D ionic/electronic conductive network may provide new strategies to design advanced conversion-type anode materials for high-performance NIBs.

关键词： Conversion-type anode Spatial confinement Fe_(2)O_(3) Graphene network Self-supporting Sodium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Irrelevant Locomotion Intention Detection for Myoelectric Assistive Lower Limb Robot Control

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical robotics and Bionics 2025年第2期7卷 655-665页

作者： Song, Xiaoyu Liu, Jiaqing Pan, Heng Rao, Haotian Wang, Can Wu, Xinyu Southern University of Science and Technology Shenzhen518055 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China

In this study, we propose a robust myoelectric intention recognition framework to recognize human locomotion mode and detect irrelevant locomotion intention. The framework is integrated into the control system of the lower limb exoskeleton robot for experimental validation. Most conventional electromyography (EMG) intention detection methods aim to accurately detect the target motion intentions but ignore the possible effects of irrelevant intentions. In traditional action intention recognition strategies, most researchers did not consider entering irrelevant action intentions into the model during training. Therefore, when using a classification model, if irrelevant action intentions are input, the model will still recognize it as a type of target action intention. That can lead to incorrect recognition results, which will cause the robot to perform wrong movements and pose a safety risk to the wearer. To detect and reject irrelevant motion intentions, we first used the dual-purpose autoencoder-guided temporal convolution network (DA-TCN) to obtain discriminative features of the surface EMG signal. Autoencoders (AE)/Variable Autoencoders (VAE) are then trained for each of the seven deep features of the target motion intention. In addition, irrelevant motion intentions are detected according to the value of their reconstruction error. The recall rate of this method for the detection of irrelevant motion intentions exceeds 99% and the accuracy rate exceeds 99%.At the same time, we replaced the TCN with the LSTM model and compared the performance of the two after adding irrelevant motion discrimination. We collected data on seven goals and three unrelated motor intentions from seven experimenters for testing and completed an online experimental validation. The motion recognition accuracy of all the experimenters can be maintained above 86%. © 2018 IEEE.

关键词： Limbs Legged locomotion Exoskeletons Robots Image color analysis Convolution Stairs Training Feature extraction Autoencoders

来源：评论

学校读者我要写书评

暂无评论

Physics-Based Predictions of the Month-by-Month Summer Western North Pacific Anomalous Anticyclone

引用

Journal of Climate 2025年第10期38卷 2187-2203页

作者： Zhu, Zhiwei Yang, Ying Liu, Boqi State Key Laboratory of Climate System Prediction and Risk Management Key Laboratory of Meteorological Disaster Ministry of Education Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters Nanjing University of Information Science and Technology Nanjing China State Key Laboratory of Severe Weather Chinese Academy of Meteorological Sciences Beijing China

This study identified the distinct predictors of the western North Pacific anomalous anticyclone (WNPAC) in June, July, and August and revealed their independent influencing mechanisms on the formation of the summer WNPAC in each corresponding month. For the June WNPAC (AC_Jun), the North Atlantic warming (NAW) in April–May induces subsequently enhanced convection over the Indian Ocean and suppressed the convection over the tropical central Pacific, leading to AC_Jun via the Gill-type response. Meanwhile, the warming tendency over the western North Pacific from February to April, which reflects the slow decay of El Niño, results in AC_Jun through Indian Ocean warming. For the July WNPAC (AC_Jul), the cooling tendency from April to June over the central and eastern tropical Pacific is the sole predictor, which results in AC_Jul through the wind–evaporation–SST feedback. For the August WNPAC (AC_Aug), the tropical Atlantic warming (TAW) in June and July and the Bering Strait sea ice slow melting (BSSM) from April to May are the two predictors. While TAW has a similar influence on AC_Aug to that of NAW on AC_Jun, BSSM makes for AC_Aug by strengthening the westerly jet and subsequently atmosphere–ocean coupling over the North Pacific. Using these predictors, three physics-based empirical models (PEMs) for the seasonal predictions of AC_Jun, AC_Jul, and AC_Aug are conducted, which all outperform the National Centers for Environmental Prediction Climate Forecast system (CFS), shedding light on improving the seasonal prediction of the East Asian summer climate. © 2025 American Meteorological Society.

关键词： Heat flux

来源：评论

学校读者我要写书评

暂无评论

An overview on mobile manipulator in nuclear applications∗

An overview on mobile manipulator in nuclear applications∗

引用

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Ou, Yue Xu, Biying Cai, Hegao Zhao, Jie Fan, Jizhuang Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin150001 China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

Nuclear power is worldwide popular and keeps rapidly growing, but manual operation in nuclear facilities is challenging by safety and workload issues. Mobile manipulators are ideal to replace human works in nuclear applications. This article reviews the development of mobile manipulators in nuclear applications over time. Then, we summarize three tasks for robots in nuclear applications and corresponding requirements, followed by an overview of the design of selected specific models. Based on the existing design, we propose the challenges for future mobile manipulators in nuclear applications. © 2022 IEEE.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

The controller architecture of dexterous hand with switchable coupling mechanism

The controller architecture of dexterous hand with switchabl...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Liu, Ziqi Jiang, Li Li, Wangyang Cheng, Ming Wu, Xiaoqiao State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150008 China

ISBN: (纸本)9781665481090

This work investigates the design of the sensor system and control system for the coupled adaptive multi-fingered dexterous hand with actively switchable modalities. Considering the specific mechanical structure characteristics of the dexterous hand, a master-slave distributed control system design approach is adopted to integrate the sensor system and control system inside the finger, which completes the mechatronic integration of the whole hand. It can realize the modularity at the finger level and simplify the system complexity. This paper also introduces a fuzzy adaptive PID control method and develops the control strategy in active switchable mode. The experimental results show that the controller architecture can adapt to the changes in the institutional characteristics of the system when the finger switches between coupled and coupled adaptive states. It can complete the high-precision tracking of the target trajectory, achieve accurate position control, and have superior real-time performance. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Terrain Classification Using Mars Raw Images Based on Deep Learning Algorithms with Application to Wheeled Planetary Rovers 11

Terrain Classification Using Mars Raw Images Based on Deep L...

引用

11th Asia-Pacific Regional Conference of the International Society for Terrain-Vehicle systems, ISTVS 2022

作者： Guo, Junlong Zhang, Xingyang Dong, Yunpeng Xue, Zhao Huang, Bo State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9781942112532

Scene information plays a crucial role in motion control, attitude perception, and path planning for wheeled planetary rovers (WPRs). Terrain recognition is the fundamental component of scene recognition. Due to the rich information, visual sensors are usually used in terrain classification. However, teleoperation delay prevents WPRs from using visual information efficiently. End-to-end learning method of deep learning (DL) that does not need complex image preprocessing was proposed to deal with this issue. This paper first built a terrain dataset (consists of loose sand, bedrock, small rock, large rock, and outcrop) using real Mars images to directly support You Only Look Once (YOLOv5) to test its performance on terrain classification. Because the capability of end-to-end training scheme is positively correlated with dataset, the performance of YOLOv5 can be significantly improved by exploiting orders of magnitude more data. The best combination of hyperparameters and models was achieved by slightly tuning YOLOv5, and data augmentation was also applied to optimize its accuracy. Furthermore, its performance was compared with two other end-to-end network architectures. Deep learning algorithms can be used in the future planetary exploration missions, such as WPRs autonomy improvement, traversability analysis, and avoiding getting trapped. Copyright © 2022 by the International Society for Terrain-Vehicle systems. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Approach to Measure Slips in Friction Contacts Using a Self-Powered Sensor 2

An Approach to Measure Slips in Friction Contacts Using a Se...

引用

2023 2nd International Conference on Materials Science and Engineering, CoMSE 2023

作者： Ba, Mingsen Qin, Wenjie Zhao, Zhenlong Sun, Yu Beijing Institute of Technology China State Key Laboratory of Engine and Powertrain System China

The accumulation of small tangential slip will occur on the contact surfaces of components in mechanical structures when subjected to cyclic loadings, which will lead to system failure. However, the small tangential slip is difficult to measure directly. In this paper, a method for measuring the contact slip by using a self-powered displacement sensor based on triboelectric nanogenerator (TENG) is proposed, and the accuracy is verified by the finite element analysis (FEA). The contact slips for a flat-on-flat contact configuration are measured by this method. When the test piece is subjected to a cyclic tangential load with a frequency of 10Hz, the average obtained slip displacement of the test piece under single load cycle is less than 10μm. Then the finite element simulation of the contact configuration is carried out using software Abaqus 6.14. The analysis results are close to the test results, which verifies the effectiveness of the measurement method. Moreover, the slips of the flat-on-flat contact configuration under different frequency and amplitude of cyclic tangential load are investigated. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Design of A Rigid-soft Hybrid Robotic Glove with Force Sensing Function

Design of A Rigid-soft Hybrid Robotic Glove with Force Sensi...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Hexin Li Li Jiang Ruichen Zhen Ming Cheng Kehan Ding State Key Laboratory of Robotics and System Harbin Institute of Technology

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Soft robotic gloves can not only provide timely, effective, safe and cheap rehabilitation training for patients with impaired movement function of hand, but also assist in completing daily grasping activities. However, most soft robotic gloves are completely composed of flexible structures. Although they have high flexibility and safety, there are problems such as poor fit and low output force. In order to solve these problems, this paper refers to the structure of the human hand and designs an articulated rigid-soft hybrid robotic glove, which combines the advantages of rigid robotic gloves and soft robotic gloves, and has high flexibility, high output force and good fit. In addition, soft robotic gloves generally lack the ability to sense the force between the human hand and the glove. Therefore, this paper designed an array flexible force sensor, and studied the structure, signal acquisition and preparation process of the sensor. Finally, a complete test platform was built to test the performance of the rigid-soft hybrid robotic glove with force sensing function. The test results show that the robotic glove has good fit and high output force, can effectively assist training and assist grasping, and can perceive the contact force.

关键词： Training Sensitivity Force Grasping Soft robotics Robot sensing systems Safety

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：