2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)最新文献_第2页

An Ankle Based Soft Active Orthotic Device Powered by Pneumatic Artificial Muscle 一种基于踝关节的气动人工肌肉软性主动矫形器

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9043948

Xinyao Hu, Chuang Luo, Haozheng Li, Liyao Jia, Chaoyang Song, Zheng Wang, Xingda Qu

{"title":"An Ankle Based Soft Active Orthotic Device Powered by Pneumatic Artificial Muscle","authors":"Xinyao Hu, Chuang Luo, Haozheng Li, Liyao Jia, Chaoyang Song, Zheng Wang, Xingda Qu","doi":"10.1109/RCAR47638.2019.9043948","DOIUrl":"https://doi.org/10.1109/RCAR47638.2019.9043948","url":null,"abstract":"Soft robotics are made by materials which have similar modulus with human musculoskeletal system. They can be used to augment the human performance without restricting the natural behavior. This paper presents a bio-inspired, ankle-based soft active orthotic device which can assist the ankle dorsiflexion during walking. This device implemented a silicone-based, fast actuating Pneumatic Artificial Muscle (PAM) to provide angular assistant force at the ankle joint. This PAM is based on the pneumatic network structure. Specific design have been made to make the PAM ergonomically compile with foot-ankle structure and facilitate the underlining application. An initial testing was first carried out to characterize the PAM. The control strategy was planned based on ankle angle information within each gait cycle. A pilot study was carried out for evaluation. The results show that this soft active orthotic device can improve the dynamic stability of the ankle joint. This device can be potentially used as real time argumentation for frail and fall-prone elderly and benefit their walking stability.","PeriodicalId":314270,"journal":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126429230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Performance of Flexible Non-contact Electrodes in Bioelectrical Signal Measurements 柔性非接触电极在生物电信号测量中的性能

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9044127

Xin Wang, Wanqing Wu, Shixiong Chen, Guanglin Li, Shuting Liu, Mingxing Zhu, Xiaochen Wang, Zhenzhen Liu, Yanbing Jiang, Dan Wang, Peng Li, O. W. Samuel

{"title":"Performance of Flexible Non-contact Electrodes in Bioelectrical Signal Measurements","authors":"Xin Wang, Wanqing Wu, Shixiong Chen, Guanglin Li, Shuting Liu, Mingxing Zhu, Xiaochen Wang, Zhenzhen Liu, Yanbing Jiang, Dan Wang, Peng Li, O. W. Samuel","doi":"10.1109/RCAR47638.2019.9044127","DOIUrl":"https://doi.org/10.1109/RCAR47638.2019.9044127","url":null,"abstract":"Electrocardiography (ECG) and electroencephalograph (EEG) are two physiological signals closely related with human health, and their measurements can help to detect various diseases in the clinic. Long-term physiological signal monitoring is usually needed to catch any possible diseases which may be missed in conventional short-term monitoring. Currently, wet electrodes are widely used in the clinic to obtain physiological signals. However, wet electrodes require adhesives or conductive gels to improve the quality of recorded signals, and may introduce skin irritation. Based on the Capacitive coupling principle, this study proposed a flexible non-contact electrode that can collect physiological electrical signals without direct contacts with the skin. Moreover, it can attach firmly than common conductive electrodes because of its flexibility. The results showed that the proposed non-contact electrode could reliably obtain high quality physiological signals, and the performance could be comparable to the conventional wet electrodes. Alpha waves could be clearly detected when the subjects closed their eyes, with the non-contact electrodes placed over the hair. This study might provide a reliable solution for long-term monitoring of physiological signals for those whose disorders could not be diagnosed over a short period of time.","PeriodicalId":314270,"journal":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128085475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

An EEG-Based Multi-Classification Method of Braking Intentions for Driver-Vehicle Interaction 基于脑电图的人车交互制动意图多分类方法

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9044151

Huikang Wang, Luzheng Bi, Weijie Fei, Ling Wang

引用次数: 2

A Compact Control System and A Myoelectric Control Method for Multi-DOFs Prosthetic Hand 一种紧凑的多自由度假手控制系统及肌电控制方法

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9044103

Bin Yang, Li Jiang, Jianhao Hu, Chongyang Li, Hong Liu

{"title":"A Compact Control System and A Myoelectric Control Method for Multi-DOFs Prosthetic Hand","authors":"Bin Yang, Li Jiang, Jianhao Hu, Chongyang Li, Hong Liu","doi":"10.1109/RCAR47638.2019.9044103","DOIUrl":"https://doi.org/10.1109/RCAR47638.2019.9044103","url":null,"abstract":"This paper introduces a compact control system for multi-DOFs prosthetic hand. Based on the optimization of sensors configuration and hardware structure of the control system, the power consumption and volume can meet the needs of the actual using. In addition, a myoelectric control method based on the principle of finite state machine (FSM) is integrated in the control system. The proposed method enables amputees to select one of the given gestures directly, and grasp objects. As the control method requires less electromyography electrodes comparing to the traditional myoelectric control method based on EMG pattern recognition, it's available for a wider range of amputees with less active muscles. To assess the performance of the proposed method, the experiments of grasping random objects by non-amputee subjects has been conducted with the 6-DOFs HIT-V prosthetic hand, and an amputee volunteer used this prosthetic hand for one day to demonstrate viability. The non-amputee experimental results indicate that subjects can select gesture correctly among seven gestures and accomplish the designed grasping tasks with a success rate up to 96.67% within a shorter time just using two electrodes, and amputee proved viability of proposed method in daily life.","PeriodicalId":314270,"journal":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130023323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Multi-Sensor Fusion Localization of Indoor Mobile Robot 室内移动机器人多传感器融合定位

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9044006

Yi Li, Li He, Xiang Zhang, Lei Zhu, Hong Zhang, Y. Guan

引用次数: 1

Third-order model based nonlinear longitudinal control for heterogeneous connected vehicle platoon 基于三阶模型的异构互联车辆队列非线性纵向控制

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9044023

Changpeng He, Yongfu Li, Jin Xu, Wei Hao

引用次数: 2

Spatio-Temporal LSTM with Aggregated Feature Learning for Human Action Recognition 基于聚合特征学习的时空LSTM人类行为识别

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9044145

Gang Chen, Qingqing Meng, Yongjun Liu, Haitao Meng

{"title":"Spatio-Temporal LSTM with Aggregated Feature Learning for Human Action Recognition","authors":"Gang Chen, Qingqing Meng, Yongjun Liu, Haitao Meng","doi":"10.1109/RCAR47638.2019.9044145","DOIUrl":"https://doi.org/10.1109/RCAR47638.2019.9044145","url":null,"abstract":"Human action recognition has received much research attention in recent years. Discriminative features learning is important for modeling the spatial and temporal evolutions of different actions. Recent works attempted to use RNN/LSTM to learn spatio-temporal features of joints. However, the features of joints are not fully explored in these conventional LSTMs, where each joint only receives context information from itself from previous frames. In this paper, we propose a LSTM network model by using aggregated feature learning strategy to extend feature representation in both spatial and temporal domains. In this model, the features of a joint are aggregated not only from all joints at previous moments, but also at current moment. Therefore, action-related features within the human skeleton sequences can be better represented and analyzed. To further optimize the network, we present a reparameterization that involves batch normalization and sparsemax classifier for the proposed LSTM network. We evaluate our approach on NTU RGB+D benchmark dataset. Experiment results demonstrate the effectiveness of the proposed approaches.","PeriodicalId":314270,"journal":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132752231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Figure-ground Image Segmentation via Semantic Information 基于语义信息的图像分割

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9043955

Ding Yuan, Jingjing Qiang, Jianfei Li, Hong Zhang, Xiaoyan Luo

引用次数: 0

Analysis of Muscle Synergy for Grip and Pinch Based on Recurrence Networks 基于递归网络的握捏肌肉协同分析

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9043985

N. Zhang, Na Wei, Shouwei Yue, Ke Li

{"title":"Analysis of Muscle Synergy for Grip and Pinch Based on Recurrence Networks","authors":"N. Zhang, Na Wei, Shouwei Yue, Ke Li","doi":"10.1109/RCAR47638.2019.9043985","DOIUrl":"https://doi.org/10.1109/RCAR47638.2019.9043985","url":null,"abstract":"The purpose of this study is to examine the muscle synergy during grip and pinch using recurrence networks (RNs). Twenty-four right-handed healthy young subjects participated in the experiment. The grip force and pinch force of the dominant hand were examined, during which the surface electromyographic (sEMG) signals were recorded from brachioradialis (BR), flexor carpi ulnaris (FCU), flexor carpi radialis (FCR), extensor digitorum communis (EDC), flexor digitorum superficialis (FDS), abductor pollicis brevis (APB), first dorsal interosseous (FDI) and abductor digiti minimi (ADM) of the dominant hand. The RNs were constructed based on the time series of sEMG signals. Two parameters-the average shortest path length ($mathcal{L}$) and the clustering coefficient ($mathcal{C}$) - were achieved from the RNs to analyze the sEMG. Results showed higher $mathcal{C}$ but lower $mathcal{L}$ in BR, FCU and FCR during grip than during pinch. In contrast, the FDI showed lower $mathcal{C}$ but higher $mathcal{L}$ during grip than during pinch. Significant differences of the two parameters were found among the three force levels in the BR, FCU, FCR. With increased force, the muscle networks of BR, FCU and FCR showed increases in $mathcal{C}$ or decreases in $mathcal{L}$. Our study suggests different muscle synergies between grip and pinch, and the extrinsic muscles play an important role in synergistic force production, the intrinsic muscles are performed well in fingers control for motor fine tasks. In addition, synergistic muscles will further coordinate in timing and strength with the force level increased. This finding might provide insights into the dynamical coordination across muscles with the force outputs and supply novel strategy for evaluating the neuromuscular function and making of the myoelectric prosthesis.","PeriodicalId":314270,"journal":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115053831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Object Detection Using Deep Learning: Single Shot Detector with a Refined Feature-fusion Structure 使用深度学习的目标检测:具有精细特征融合结构的单镜头检测器

2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2019-08-01 DOI: 10.1109/RCAR47638.2019.9044027

Shili Chen, Jie Hong, Tao Zhang, Jian Li, Y. Guan

{"title":"Object Detection Using Deep Learning: Single Shot Detector with a Refined Feature-fusion Structure","authors":"Shili Chen, Jie Hong, Tao Zhang, Jian Li, Y. Guan","doi":"10.1109/RCAR47638.2019.9044027","DOIUrl":"https://doi.org/10.1109/RCAR47638.2019.9044027","url":null,"abstract":"In order to improve the detection accuracy of objects at different scales, the most recent studies applied multilayer architecture. However, the extracted low-level feature in the shallow layers may not work perfectly on the detection performance due to its less semantic information, especially for small objects. In this paper, we propose a refined feature-fusion structure to be integrated with single shot detector (SSD). To obtain the rich representation ability for feature mapping, in the fusion block, the deconvolution operation is basically applied to fuse high-level semantic features and low-level semantic features. It is noteworthy that in the proposed framework, the feature pyramid network is modified to better describe the features by the skip connection. An adaptive weighted connection is designed at the feature-fusion block, which further enhances the performance of the detection. On PASCAL VOC2007 test set, the experimental results show that the mAP of the proposed network is higher than SSD and deconvolutional single shot detector (DSSD) by 2.03% and 0.63%, respectively. Meanwhile, the speed of our method is as 2.2 times fast as the DSSD. Furthermore, the mAP of our refined feature-fusion structure SSD is 6.2% higher than SSD on the small object test set of PASCAL VOC2007, which verifies the effectiveness of the proposed model.","PeriodicalId":314270,"journal":{"name":"2019 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"617 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116454647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7