检索结果-内蒙古大学图书馆

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

作者： Ding, Kehan Jiang, Li Zhen, Ruichen State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819964888

The wrist can greatly enhance the manipulative performance of dexterous hands. In addition, due to the flexibility of soft materials, the soft wrist has obvious advantages in environmental adaptability and safety. However, existing soft wrists often have small motion curvatures and cannot modulate stiffness. Inspired by the human wrist, we proposed a rigid-soft pneumatic wrist design with fixed axes, realizing variable stiffness through jamming mechanisms. The wrist is composed of two rotatory joints in series to achieve pronation/supination and flexion/extension motions. Each joint is driven by two opposite-mounted actuators, resulting in active bidirectional movement. The pre-stretched mounting of pneumatic actuators eliminates the stiffness torque effects. Both joints have independent jamming stiffening mechanisms controlled by air pressure and require no additional power source, which makes the stiffness control more flexible. Experimental results demonstrated that the maximum output torques of the two joints reached 1.18 Nm and 1.40 Nm, and the jamming mechanism increased the stiffness of the joints by 55.3% and 67.2% in the practical test, respectively. The proposed rigid-soft wrist provides a feasible solution for enhancing the manipulative ability of soft dexterous hands. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Pneumatic actuators

来源：评论

学校读者我要写书评

暂无评论

Optimizing Dataset Configuration for Improving Convolutional Neural Networks Performance in Chest X-ray Image Classification 8

Optimizing Dataset Configuration for Improving Convolutional...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： He, Zengmin Ren, Yi Wang, Honggang Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350302455

Chest X-ray (CXR) is essential for physicians to diagnose lung diseases in clinical medicine. With the development of computer and deep learning techniques, creating CXR datasets to train convolutional neural networks (CNNs) has become a popular research topic. However, there are still challenges in creating datasets due to class imbalance and the ratio setting of datasets. This study investigated the impact of class imbalance and the ratio of training, validation, and test sets on CNNs classification performance by optimizing the dataset configuration. This was achieved by directly modifying the ratio, applying oversampling based on the adaptive contrast enhancement (ACE) algorithm, and random undersampling to balance the dataset classes, followed by modifying the ratio again. Therefore, seven datasets were obtained, which were utilized to individually train four CNNs based on transfer learning and fine-tuning techniques. Evaluation metrics based on the confusion matrix were utilized to demonstrate the enhanced classification performance of CNNs. The results indicated that at least 17% of the accuracy of CNNs trained by the dataset with modified ratios was improved as compared with the dataset with an unreasonable initial configuration. Additionally, the overall evaluation metrics of CNNs were further improved by balancing the dataset classes and modifying the ratios. ChexNet demonstrated the best classification performance among the four CNNs, as evidenced by the area under the receiver operating characteristic (ROC) curves (AUC). Furthermore, ChexNet was trained by a class balanced dataset with a ratio of 7:2:1, resulting in the best evaluation metrics, including F1 Score, balanced accuracy, accuracy, recall, specificity, and precision, which were 97.81%, 97.78%, 97.78%, 98.73%, 96.84%, and 96.89%, respectively. Therefore, optimizing dataset configuration can effectively improve the performance of CNNs, providing empirical guidance for researchers in creating dat

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Improving CNNs in Medical Image Classification 8

Data Augmentation for Improving CNNs in Medical Image Classi...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Ren, Yi He, Zengmin Deng, Yang Huang, Bo Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350302455

Medical image is essential for physicians to diagnose diseases. And convolutional neural networks (CNNs) have gained momentum for computer-aided diagnosis (CAD) medical image. However, there are still challenges in CNNs related to a lack of data and class-imbalanced datasets. Data augmentation is utilized to address the issues mentioned above. In this study, the Pseudo-color enhancement algorithm (OCEAN and TWILIGHT), common linear transform, CLAHE enhancement, and K-means clustering algorithm were applied to pneumonia X-ray images for data augmentation. Thus, five processed datasets were finally obtained. The results indicated that five data-augmentation methods effectively improved the performance of CNNs for the pneumonia X-ray images binary classification detection, in which the CLAHE enhancement and OCEAN enhancement methods had the accuracy and F1 Score with 97.42%, 97.19%, and 97.42%, 98.36%, respectively. DenseNet121 showed the best classification performance of four CNNs utilized in this study, as evidenced by the area under the receiver operating characteristic (ROC) curves (AUC). To verify the generalizability of the two enhancement methods, CLAHE and OCEAN enhancement methods were applied to the Magnetic Resonance Imaging (MRI) dataset of Alzheimer's disease, which had the accuracy and F1 Score with 98.15% , 98.15%, and 97.22%, 97.68%, respectively. Therefore, these simple and efficient data-augmentation methods effectively improve the performance of CNNs for diagnosing medical image, which can provide theoretical reference for physicians to diagnose the above two diseases, and advance the application of clinical medicine. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Solving Time-Varying Linear Equations and Its Application in Motion Tracking of Redundant Robots

A Novel Approach for Solving Time-Varying Linear Equations a...

引用

2023 International Conference on Frontiers of robotics and Software Engineering, FRSE 2023

作者： Yin, Hong Jin, Hongzhe Zhao, Jie Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350301113

Solving time-varying linear equations is a common problem in many fields. In this article, a novel approach is proposed based on the cost function constructed by the mixed error, which is made up of the residual error and its integration. The merits of the novel approach include high accuracy, noise immunity, and asymptotic convergence. Since the derivative information of time-varying signals is used in the proposed method, a proportional-integral differentiator is designed based on the mixed estimation error for the first derivative estimation. The proposed differentiator has a high degree of precision, asymptotic convergence, and no chattering. In addition, theoretical analyses prove the convergence of the proposed optimal strategy and differentiator. Simulation results validate the effectiveness and superiority of the proposed strategy and the designed differentiator. Finally, the proposed approach is employed in the motion tracking of redundant robots. © 2023 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

GCA-Net: A Global Context Aggregation Network for Effective Optical Flow 49

GCA-Net: A Global Context Aggregation Network for Effective ...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Xie, Tao Gao, Jinghan Wang, Ke Li, Ruifeng Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350331820

Optical flow seeks to estimate the per-pixel 2D motion between two frames by identifying corresponding pixels. Current flow estimators typically involve per-pixel feature extraction, multi-scale 4D correlation volume construction, and iterative flow field updates through a Conv-GRU module. However, the locality of convolutional features in these methods renders the calculated correlations vulnerable to different noises. In addition, the Conv-GRU module of these methods is only executed with a convolution layer, which is incapable of exploiting context clues from larger window sizes even inside the image being queried itself, thus raising it more difficult for the model to process images with challenging regions, e.g., textureless areas. To this end, we introduce GCA-Net, a global context aggregation network for credible yet effective optical flow estimation. More specifically, we propose a highly efficient multi-scale transformer (MSFormer) layer which enables the per-pixel feature to aggregate long-range information from other features, hence building more accurate 4D correlation volumes. Besides, we develop an attention-enhanced Conv-GRU block (AttGRU) that can incorporate information alongside a larger context window even within itself empowering our network to estimate optical flow in even the most challenging regions. Experimentally, we demonstrate that GCA-Net outperforms previous state-of-the-art methods by large margins on Sintel (Final) and KITTI 2015 (background and foreground) benchmarks. © 2023 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

An Effective Rotor-Shape Optimization Method for IPM Motor with 1/2 Slot per Phase per Pole

An Effective Rotor-Shape Optimization Method for IPM Motor w...

引用

2023 IEEE International Conference on Applied Superconductivity and Electromagnetic Devices, ASEMD 2023

作者： Yu, Guodong Sun, Shuqi Li, Junlong Xiao, Lijun Xu, Yongxiang Zou, Jibin Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9798350301571

Although IPM motor with 1/2 slot per phase per pole has a relatively less rotor loss in comparison with other fractional slot concentrated winding (FSCW), the problems of THD of back-EMF and cogging torque are worse, which limits its application in electric vehicles and other industry fields. This paper proposes an effective rotor-shape optimization method to suppress both THD of back-EMF and cogging torque for improving torque ripple problem. Different from the prevalent rotor optimization methods, the proposed rotor-shape optimization method associates both shape function optimization of rotor surface with PM shaping, which can effectively decrease optimization parameters, and enhance optimization efficiency. To clarify the optimization strategy, the back-EMF and cogging torque for this PM motor with 1/2 slot per phase per pole are analyzed firstly. Then, the proposed optimization method is presented in detail. Finally, the optimized IPM motor is prototyped and its experimental results verifies the effectiveness of the proposed optimization method. © 2023 IEEE.

关键词： back-EMF cogging torque IPM motor optimization method

来源：评论

学校读者我要写书评

暂无评论

Dual-Arm Dynamic Planning with Considering Arm Reachability Constraint in Task Space 16th

Dual-Arm Dynamic Planning with Considering Arm Reachability ...

引用

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

作者： Shu, Xin Fan, Xinyang Min, Kang Ji, Zhu Ni, Fenglei Liu, Hong State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

ISBN: (纸本)9789819964888

This paper aims to address the issue of planning dual-arm motions in scenarios involving tracking dynamic desired pose and obstacle avoidance. In situations where dual-arm motion requires synchronous behavior, inflexible planning, encountering obstacles, and beyond-the-arm motion capability may lead to task failure. To overcome these issues, we propose a dynamic-system-based method for dual-arm collaborative planning. The method can coordinate the motions of dual arms while keeping synchronous behavior in tracking the moving target and avoiding obstacles. Meanwhile, we incorporate the reachability by modeling the motion boundary to ensure that the arms moving within the reachable space. The experiment successfully verified the above scenarios, showcasing its adaptability in dual-arm planning and its potential applicability in dual-arm applications such as transportation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A Braille Reading system Based on Electrotactile Display With Flexible Electrode Array

引用

IEEE/CAA Journal of Automatica Sinica 2022年第4期9卷 735-737页

作者： Ziliang Zhou Yicheng Yang Honghai Liu IEEE the State Key Laboratory of Mechanical System and Vibration Shanghai Jiao Tong University the State Key Laboratory of Robotics and Systems Harbin Institute of Technology Shenzhen

Dear editor,Due to visual impairment and lack of social attention,the reading problem of the blind has not been well *** existing Braille reading devices still have many problems and are not accepted by the *** paper developed a portable Braille reading system based on electrotactile display *** proposed system is composed of a six-channel electrotactile stimulator,a flexible electrode array for Braille display and a graphical user interface(GUI)for monitoring and *** on the flexibility of the system,two Braille reading strategies have been designed:spatial mode and sequential *** system was preliminary tested by six sighted *** results showed that subjects were able to recognize Braille characters with more than 80%accuracy within less than 10 seconds for the initial *** to existing Braille reading systems,this system is portable,wearable and flexible in control.

关键词： portable editor Bra

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Navigation for Robots Based on Hippocampus Episode Cognition

引用

Journal of Bionic Engineering 2024年第1期21卷 288-302页

作者： Jinsheng Yuan Wei Guo Zhiyuan Hou Fusheng Zha Mantian Li Pengfei Wang Lining Sun State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150001China Shenzhen Academy of Aerospace Technology Shenzhen 518057China School of Mechanical and Electrical Engineering Lanzhou University of TechnologyLanzhou 730050China

Artificial intelligence is currently achieving impressive success in all ***,autonomous navigation remains a major challenge for *** learning is used for target navigation to simulate the interaction between the brain and the environment at the behavioral level,but the Artificial Neural Network trained by reinforcement learning cannot match the autonomous mobility of humans and *** hippocampus–striatum circuits are considered as key circuits for target navigation planning and *** paper aims to construct a bionic navigation model of reinforcement learning corresponding to the nervous system to improve the autonomous navigation performance of the *** ventral striatum is considered to be the behavioral evaluation region,and the hippocampal–striatum circuit constitutes the position–reward *** this paper,a set of episode cognition and reinforcement learning system simulating the mechanism of hippocampus and ventral striatum is constructed,which is used to provide target guidance for the robot to perform autonomous *** with traditional methods,this system reflects the high efficiency of learning and better Environmental *** research is an exploration of the intersection and fusion of artificial intelligence and neuroscience,which is conducive to the development of artificial intelligence and the understanding of the nervous system.

关键词： Episode cognition Reinforcement learning Hippocampus Robot navigation

来源：评论

学校读者我要写书评

暂无评论

Structural Design and Experiment of a Small Wheel-legged Mobile Robot with Variable Configuration 20

Structural Design and Experiment of a Small Wheel-legged Mob...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Cui, Xiulong Fan, Jizhuang Dong, Zhihui Ou, Yue Zhao, Jie Harbin Institute of Technology The State Key Laboratory of Robotics and System Harbin150001 China

ISBN: (纸本)9798350320831

In this paper, we made an improved design on the traditional quadruped robot structure and developed a new small wheel-legged mobile robot structure. It has four legged configurations, which can be selected according to different situations, improving the mobility and operability of the robot. In wheeled mode, the robot can adjust its center of gravity according to actual needs. Including the rotational degree of freedom of the wheel, each leg has four degrees of freedom. Each leg adopts a series structure and moves the knee drive motor to the fuselage position using a parallel four-link mechanism and is symmetrically arranged with the hip drive motor. A wheel is installed at the end of the shank, and a DC brushless motor is built inside it, enabling the robot to have the function of wheeled motion. This article introduces the details of the wheel-legged robot, emphasizing the innovative design of the physical structure and the diversity of deformation. The forward kinematics was analyzed. Based on the full-elbow configuration (a type of legged configuration), a cycloidal motion optimization simulation was completed for the single leg structure. Simulation experiment has proven that the optimized robot's single leg motion is smoother. Finally, we conducted a typical experiment using an embedded controller to control single leg motion. The experimental results verify that the optimized cycloidal motion of the robot meets the desired motion effect. © 2023 IEEE.

关键词： Mobile robots

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：