检索结果-内蒙古大学图书馆

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Ma, Yue Zheng, Liangsheng Yi, Zhengkun Xiao, Yang Wang, Can Wu, Xinyu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Chongqing University of Posts and Telecommunications

ISBN: (纸本)9781665436786

The brain-computer interfaces (BCI) technology is able to help dysfunctional people recover their motor functions. Electroencephalography (EEG) is an effective noninvasive method to construct BCI. Motor imagery (MI) paradigm can directly reflect the motor intention of user without additional stimulation equipment in EEG-BCI. The feature extraction methods are the key components to improve the accuracy of MI classification. Traditional feature extraction methods like CSP that only extract features in a single domain or two domains. In this study, we propose two novel feature selection method, short-time Fourier transform covariance and its selection method, which are aiming to extract spatial-time-frequency features simultaneously. In order to evaluate the proposed features, the BCI Competition IV Data Set IIb is employed to test the classification accuracy. By comparing the average accuracy of novel TSGSP method, the proposed method is more stable than TSGSP about 6% and the accuracy is just decrease about 0.5% at the same time. The average accuracy of 83.8% over all subjects is obtained. Superior classification performance results show that our proposed method has great potential, which is helpful for the further development and application of BCI technology for motor imaging in the field of neurorehabilitation. © 2021 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A multi-task learning convolutional neural network for object pose estimation

A multi-task learning convolutional neural network for objec...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Wang, Yurui Jin, Shaokun Ou, Yongsheng Shenzhen Institutes of Advanced Technology CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Beijing China University of Chinese Academy of Sciences Beijing China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9781728163215

Estimating 6D poses of objects from RGB images is very crucial for robots to interact with the surrounding environment and to cooperate with humans. It is a challenging problem due to the various shapes of objects, the occlusions among objects, as well as the complexity of the scene. In this study, we present a new multi-task convolutional neural network for 6D object pose estimation, which also learns the object region in the image to further improve the estimation result. A weighted loss computed from the training samples is adopted to guarantee that the components of the estimated pose are equally accurate. Additionally, we sythesize new virtual data based on the existing training data so as to overcome the possible adverse situation caused by insufficiency of training data. Experiments on the YCB-video dataset are undertaken to validate the effectiveness of the proposed method. © 2019 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Design and Path Planning of Massagebot: one Massaging Robot Climbing along the Acupuncture Points

Design and Path Planning of Massagebot: one Massaging Robot ...

引用

IEEE International Conference on Information and Automation

作者： Hongli Chen Xinyu Wu Wei Feng Tiantian Xu Yong He Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Science China

ISBN: (纸本)9781509041039

This paper describes a 2 DOF (Degrees of Freedom) massaging robot prototype: Massagebot, which is equipped with two kinds of massage structure and can realize two kinds of massage by scratching and shaking on user's back. Massagebot has two-wheel gripper, and two-triangular structure of body with good stability. In terms of path planning, we proposed a location algorithm based on simplified acupuncture points, where the SOM (Self-organizing Feature Map) neural networks, image processing and pattern recognition are combined together. In one hand, an innovative idea was proposed that using SOM neural network to cluster and simplify acupuncture points to several classes. In the other hand, there is an acupuncture point recognition algorithm presented in path planning.

关键词： Massaging robot climbing path planning SOM neural network

来源：评论

学校读者我要写书评

暂无评论

A Learning Human-Based Method For Peg-In-Hole Assembly Using ELM

A Learning Human-Based Method For Peg-In-Hole Assembly Using...

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Sheng, Juyi Liu, Sheng Zhu, Bing Zhu, Chi Ou, Yongsheng Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing101408 China Maebashi Institute of Technology Japan

ISBN: (纸本)9798350327182

This paper focuses on using sensor information to adjust the position for assembly in the presence of uncertainty error in vision. Firstly, a human demonstration of the peg-in-hole assembly is provided, and the data is collected for the next step of training. We start with a human demonstration and collect training data. A network is trained with 6D Force/Torque sensor (F/T sensor) as input and a strategy of which direction the robot end-effector needs to move as output. An algorithm using Extreme Learning Machines (ELM) search is proposed. This is a human-like method of searching for holes. We validated the effectiveness of our method on a KUKA iiwa 7 robot arm. © 2023 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Depth Image Super-resolution via Two-Branch Network 6th

Depth Image Super-resolution via Two-Branch Network

引用

6th International Conference on Cognitive systems and Signal Processing, ICCSIP 2021

作者： Guo, Jiaxin Xiong, Rong Ou, Yongsheng Wang, Lin Liu, Chao Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Shenzhen China

ISBN: (纸本)9789811692468

With the continuous development of sensors, a number of inexpensive and effective depth cameras have shown up, which have greatly contributed to the development of autonomous driving and 3D reconstruction technologies. However, the depth images captured by low-cost depth cameras are low-resolution, which is difficult to meet the needs of practical applications. We propose a two-branch network to achieve depth map super-resolution with high-resolution guidance image, which can be viewed as a prior to guide the low-resolution depth map to restore the missing high-frequency details of structures. To emphasize the guidance role of high-resolution images, we use spatially-variant kernels based on the guidance feature map to replace the original convolution kernels. In addition, in order to extract the feature maps of the depth images more effectively, we add the channel attention mechanism between convolution layers. Our network is trained end-to-end, supporting various sizes of input images because the network backbone uses full convolution and no fully connected layers. The proposal model is trained only on a certain dataset under three super-resolution factors and utilized directly on other datasets without fine-tuning. We show the effectiveness of our model by comparing it with state-of-art methods. © 2022, 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

A new remote sensing image dataset for large-scale remote sensing detection

A new remote sensing image dataset for large-scale remote se...

引用

2019 IEEE International Conference on Real-Time Computing and robotics, RCAR 2019

作者： Xie, Dongyang Cheng, Jun Tao, Dapeng Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Chinese University o f Hong Kong Hong Kong999077 Hong Kong

ISBN: (纸本)9781728137261

- With recent developments in sensor technology, remote sensing is playing an increasingly important role in military and civilian life such as town planning, mapping, resource and crop monitoring, and disaster prevention. These applications are based on remote sensing images, which ideally comprehensively reflect the information needed. However, remote sensing images are unusual, in the sense that they tend to be larger scale, contain more irrelevant information, and contain more complex scenes. These factors greatly increase the difficulty of the object detection for remote sensing task and, moreover, there is currently a lack of large datasets. Here we build a new image dataset for object detection in remote sensing. The dataset includes 108,989 images in two categories, with the images cropped from large-scale remote sensing images. To increase the relevance of our large-scale remote sensing images, we include the same area imaged at different time points. We test the dataset using faster R-CNN detection models trained on different CNN networks. In addition, we use fixed faster R-CNN for detection in large-scale remote sensing images using a model trained with VGGI6. Our experimental results show that the proposed dataset provides a new benchmark for remote sensing detection, and the fIXed faster R-CNN detected correctly in large-scale remote sensing images. © 2018 IEEE

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Assessment of Lower Limb Muscle Fatigue Through Fusion of sEMG and VMG Signals 17

A Comprehensive Assessment of Lower Limb Muscle Fatigue Thro...

引用

17th International Convention on Rehabilitation Engineering and Assistive Technology, i-CREATe 2024

作者： Pan, Heng Song, Xiaoyu Rao, Haotian Wang, Can Wu, Xinyu Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent Sys-tem Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9798350355154

The measurement of lower limb muscle fatigue is crucial for Human-Machine Interaction (HMI) and the prevention of muscle injuries. This study aims to explore a method for assessing lower limb fatigue based on surface electromyography (sEMG) and vibromyography (VMG) signals, with the aim of improving the accuracy and sensitivity of muscle fatigue assessment. The muscle fatigue induction experiment was conducted by subjecting participants to sustained isometric contractions at 50 % of their maximal voluntary contraction (MV C) to induce a state of complete muscle fatigue, with five subjects participating. We employed the wavelet scattering technique to extract features from the sEMG and VMG signals, subsequently analyzing the combination of peak amplitude, root mean square (RMS), and median frequency (MDF) as indicators of muscle fatigue. By analyzing the differences and correlations between these fatigue indicators, it is possible to correlate muscle contraction intensity and muscle synergy, thereby making a detailed and reliable physiological assessment of muscle fatigue and comprehensively understanding the fa-tigue mechanism. This study provides a new assessment method for sports medicine and rehabilitation engineering, and provides theoretical support for fatigue monitoring and rehabilitation training. © 2024 IEEE.

关键词： fatigue-based feedback Muscle fatigue surface electromyo-graphy (sEMG) vibromyography (VMG) wavelet scattering

来源：评论

学校读者我要写书评

暂无评论

A platform for integrated spectrometers based on solution-processable semiconductors

引用

Light(Science & Applications) 2023年第9期12卷 1739-1748页

作者： Yanhao Li Xiong Jiang Yimu Chen Yuhan Wang Yunkai Wu De Yu Kaiyang Wang Sai Bai Shumin Xiao Qinghai Song Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Guangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic SystemsHarbin Institute of Technology(Shenzhen)ShenzhenGuangdong 518055China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengduSichuan 611731China Collaborative Innovation Center of Extreme Optics Shanxi UniversityTaiyuanShan`xi 030006China

Acquiring real-time spectral information in point-of-care diagnosis,internet-of-thing,and other lab-on-chip applications require spectrometers with hetero-integration capability and miniaturized *** to conventional semiconductors integrated by heteroepitaxy,solution-processable semiconductors provide a much-flexible integration platform due to their solution-processability,and,therefore,more suitable for the multi-material integrated ***,solution-processable semiconductors are usually incompatible with the micro-fabrication *** work proposes a facile and universal platform to fabricate integrated spectrometers with semiconductor substitutability by unprecedently involving the conjugated mode of the bound states in the continuum(conjugated-BIC)***,exploiting the conjugated-BIC photonics,which remains unexplored in conventional lasing studies,renders the broadband photodiodes with ultra-narrowband detection ability,detection wavelength tunability,and on-chip integration ability while ensuring the device *** based on these ultra-narrowband photodiode arrays exhibit high spectral resolution and wide/tunable spectral *** fabrication processes are compatible with solution-processable semiconductors photodiodes like perovskites and quantum dots,which can be potentially extended to conventional *** from the spectrometers directly constitute the incident spectra without being computation-intensive,latency-sensitive,and *** an example,the integrated spectrometers based on perovskite photodiodes are capable of realizing narrowband/broadband light reconstruction and in-situ hyperspectral imaging.

关键词： semiconductors process integration

来源：评论

学校读者我要写书评

暂无评论

3D Source Tracking Using a Position-Unknown AOA Sensor with Measurement Drift and UAV Moving Direction Optimization

3D Source Tracking Using a Position-Unknown AOA Sensor with ...

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Xu, Rongrong Xu, Sheng Cao, Kaimin Li, Xianliang Wang, Jialiang Cao, Wujing Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China China Nanhu Academy of Electronics and Information Technology Robotics Laboratory 314051 China University of Chinese Academy of Sciences Beijing101408 China

ISBN: (纸本)9798350372601

This work solves the angle-of-arrival (AOA) source tracking problem in 3-dimensional (3D) space utilizing a position-unknown unmanned aerial vehicle (UAV). An AOA sensor is carried by a mobile UAV, and the conventional self-positioning module, such as the global positioning system (GPS), is not allowed due to environmental limitations. Thus, to guarantee the feasibility of this source tracking problem, at least two position-known landmarks are required. Firstly, the detailed problem formulation is provided with the consideration of measurement drift caused by sensor-vehicle installation errors. Secondly, all the unknown states are estimated using a proposed extended Kalman filter (EKF). Thirdly, a UAV moving direction optimization algorithm is developed to promote the estimation accuracies of the source, UAV and measurement drift. Finally, simulation examples demonstrate the characteristics of the proposed method. © 2024 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Preliminary study of online real-time control system for lower extremity exoskeletons based on EEG and sEMG fusion

Preliminary study of online real-time control system for low...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Li, Wenju Shao, keyong Zhu, Chi Ma, Yue Cao, Wujing Yin, Meng Yang, Lijun Luo, Mingxiang Wu, Xinyu Northeast Petroleum University School of Electrical Engineering Information Daqing China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Guangdong Shenzhen518055 China Maebashi Institute of Technology Department of Systems Life Engineering Maebashi3710132 Japan

ISBN: (纸本)9781665481090

Motion imaging (MI) is widely used in exoskele-ton robot control direction. However, online real-time con-trol of exoskeletons based on biological signals is difficult to achieve. Because the anti-interference of biological signals in real life is poor and affected by individual differences, the control of auxiliary equipment by the realization of human-machine interface is still facing great challenges. In this paper, a human-machine interface (HMI) based on hybrid biological signals is designed and online real-time control of lower extremity exoskeletons is realized. Based on a comprehensive analysis of human walking, the HMI uses the electromyography signals (upper extremities) and EEG signals generated during real exercise as input signals. Different analysis methods are designed for different modal signals. We extracted four features of sEMG signals to distinguish between different movement processes in the human body. For EEG signals, the use of Independent Component Analysis (ICA) increases the robustness of the system. Event-related desynchronization/synchronization (ERS/ERD) and power spectral densities are reused for analysis from the perspective of the interaction of multiple information in the channel, time and frequency domains. The human-machine interface integrates EEG and EMG multimodal biological signals, and the average recognition accuracy of different subjects has reached 93.7%. In order to increase the recognition accuracy of practical applications and reduce the differences between different individuals, a window voting mechanism is designed. Healthy subjects were tested, and the recognition accuracy of the lower limb exoskeleton online real-time assistance system reached 99%, with high accuracy and reliability. © 2022 IEEE.

关键词： Real time control

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：