2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)最新文献_第3页

Asynchronous steady-state visual evoked potential brain-computer interface application: True and false positive rate comparison between with and without eye-tracking switch paradigms 非同步稳态视觉诱发电位脑机接口应用:带与不带眼动追踪切换范式的真阳性率和假阳性率比较

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517381

Jun Xie, Huanqing Zhang, Yi Liu, Peng Fang, Hongwei Yu, Liushi He, Guanglin Li, Song Yuan, Guanghua Xu, Min Li

{"title":"Asynchronous steady-state visual evoked potential brain-computer interface application: True and false positive rate comparison between with and without eye-tracking switch paradigms","authors":"Jun Xie, Huanqing Zhang, Yi Liu, Peng Fang, Hongwei Yu, Liushi He, Guanglin Li, Song Yuan, Guanghua Xu, Min Li","doi":"10.1109/RCAR52367.2021.9517381","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517381","url":null,"abstract":"Due to the bypass of muscle activity or peripheral nerve control, brain-computer interface (BCI) technique has advantages in different fields such as medical field for the rehabilitation of paralyzed patients. Steady-state visual evoked potential (SSVEP) has been widely adopted in BCI applications. SSVEP based BCIs have the advantages of high information transfer rate, less or no need of training, and strong anti-interference, which could be used in the more natural asynchronous BCI application with control of the users rather than the operant system of the synchronous mode. In order to solve the problem of high false positive rate (FPR) in common asynchronous SSVEP BCI applications, this paper proposed an eye-tracking switch based BCI paradigm to reduce the FPR and to improve the performance of the asynchronous BCI system. In the proposed paradigm, the fixation point position instead of EEG signal is used to determine whether the system is in idle state. Experimental results showed that when eye-tracking switch was applied in the asynchronous SSVEP BCI, the FPR was reduced to less than 10% and the recognition accuracy (i.e., the true positive rate, TPR) can also be improved to a certain extent, which proved the applicability of the eye-tracking switch in asynchronous BCI applications.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126361034","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

UCAS-Hand: An Underactuated Powered Hand Exoskeleton for Assisting Grasping Task UCAS-Hand:辅助抓取任务的欠驱动动力手外骨骼

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517383

Houcheng Li, Long Cheng, Zhengwei Li, Guotao Li

引用次数: 4

Deep Convolutional Neural Network Transfer Learning Optimization Based on Visual Interpretation 基于视觉解释的深度卷积神经网络迁移学习优化

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517519

Yibo Xu, Jiongming Su, Fengtao Xiang, Ce Guo, Haoran Ren, Huimin Lu

{"title":"Deep Convolutional Neural Network Transfer Learning Optimization Based on Visual Interpretation","authors":"Yibo Xu, Jiongming Su, Fengtao Xiang, Ce Guo, Haoran Ren, Huimin Lu","doi":"10.1109/RCAR52367.2021.9517519","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517519","url":null,"abstract":"In image classification tasks, the training of deep convolutional neural networks generally requires a large amount of data, and due to the constraints of environment, resources and time, it is of great practical importance to use fewer training samples to obtain a higher recognition rate in the shortest possible time. A deep convolutional neural network transfer learning optimization method based on visual interpretation is proposed for a specific image classification task. Firstly, we use class activation mapping visualization as a visual interpretation, output the class activation heat map of the validation set images, and analyze the reasons for misrecognition of the images. Secondly, we introduce “feedback” by pre-recognizing and visualizing the optimized dataset with the model trained on the original dataset, selecting the images that have a greater impact on improving the recognition rate, and maximizing the impact of the optimized images on the original model. Finally, the model is retrained on the optimized training set. The experimental results show that this method can effectively improve the recognition rate of the transfer learning model for image classification.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132306619","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

Lower Limb Exoskeleton Design Based on Knee Joint Assistance 基于膝关节辅助的下肢外骨骼设计

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517623

Peng Jiang, Ye Wang, Tianqi Shao, Changsoo Han, Lin Wang, Guanglin Li

{"title":"Lower Limb Exoskeleton Design Based on Knee Joint Assistance","authors":"Peng Jiang, Ye Wang, Tianqi Shao, Changsoo Han, Lin Wang, Guanglin Li","doi":"10.1109/RCAR52367.2021.9517623","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517623","url":null,"abstract":"Human mobility is vital to daily activities and can be directly linked to the living quality. This is an especially severe problem for the patients with walking dysfunction. There is a great need to develop viable mobility solutions to assist individuals and improve their living quality. Wearable gait-assisted exoskeletons are an effective solution to this growing problem. This paper presents a passive lower limb exoskeleton which can work on hip and knee joints for gait assistance. The hip exoskeleton is designed based on specially shaped torsion springs that work with cams for gravity compensation of the human thigh, converting the torque of the built-in torsion springs into a balanced torque of the hip and knee joints in the later stages of the gait stance phase to overcome the effects of gravity. The knee exoskeleton is designed with reference to a new spring-loaded gravity balanced structure used to carry single-degree-of-freedom rotational loads. When worn, it can help the lower leg to push out during gait swing state to compensate for falls due to the lack of lower leg swing. After the exoskeleton prototype was completed, 3D motion capture experiments were performed to obtain gait parameters. Finally, the effectiveness of the exoskeleton in assisting patients with walking dysfunction was verified using OpenSim simulation software.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131761699","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

Automatic Venous Segmentation in Venipuncture Robot Using Deep Learning 基于深度学习的静脉穿刺机器人自动静脉分割

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517605

Tianbao He, Chuangqiang Guo, Li-Gen Jiang, Hansong Liu

{"title":"Automatic Venous Segmentation in Venipuncture Robot Using Deep Learning","authors":"Tianbao He, Chuangqiang Guo, Li-Gen Jiang, Hansong Liu","doi":"10.1109/RCAR52367.2021.9517605","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517605","url":null,"abstract":"Vein identification plays a pivotal role in realizing automatic venipuncture, and it has become a difficulty to segment the veins efficiently as well as accurately in the research of full-automatic venipuncture robots. Most studies in the field of vein segmentation have only focused on traditional image processing methods, the segmentation accuracy and generalization performance of which are poor. Therefore, we propose an automatic image segmentation algorithm using the U-Net model with the attention mechanism (Attention-UNet) which can suppress unnecessary features. Besides, the encoder-decoder and the skip-connection structure are applied for multi-scale feature recognition so that the segmentation accuracy can be improved. Meanwhile, on digital arm images for the vein segmentation data set (DAIVS data set), the newly-built human forearm veins data set, the effectiveness of the proposed method in vein segmentation is verified. Finally, we conduct experiments to acquire and process venous images with the Attention-UNet in real-time on the venipuncture robot. These results indicate that machine vision has better performance in complex visual tasks and can be translated into clinical application.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133316914","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: 5

Research on Graph-Based SLAM for UVC Disinfection Robot UVC消毒机器人基于图的SLAM研究

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517506

Xuan Tan, Hui Zhang, Xidong Zhou, Hang Zhong, Li Liu

引用次数: 1

Design of a Battery Carrying Barge for Enhancing Autonomous Sailboat's Endurance Capacity 提高自主帆船续航能力的载电池驳船设计

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517585

Cheng Liang, Rong-Shyang Ou, Bairun Lin, Xiaoqiang Ji, R. Cheung, Huihuan Qian

引用次数: 1

Saturated PD with sliding mode control method for 4-DOF tower crane systems 四自由度塔吊系统饱和PD滑模控制方法

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517576

Weijie Huang, Menghua Zhang, Fuqiang Sun, Jin Zhang, Changhui Ma, Zaixing Zhu

{"title":"Saturated PD with sliding mode control method for 4-DOF tower crane systems","authors":"Weijie Huang, Menghua Zhang, Fuqiang Sun, Jin Zhang, Changhui Ma, Zaixing Zhu","doi":"10.1109/RCAR52367.2021.9517576","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517576","url":null,"abstract":"A new saturated PD with sliding mode control method (or saturated PD-SMC in short) was designed by this paper for 4-DOF tower crane systems. The design was based on uncertain dynamics, external disturbances, and control input constraints. By means of jib/trolly-position/velocity and payload swing-feedback with limited control inputs, the designed control method, which is model free, can achieve accurate positioning and rapid swing suppression and elimination. Besides, by adopting the advantages of simple structure, the designed control method can be easily realized in the applications of the PD control, compared with existing control methods. This method also has strong robustness of the SMC method regarding to model uncertainties and external disturbances. As a result, this design avoids the requirements of accurate model knowledge concerned with the SMC method, as well as rapid payload swing reduction of the swing suppression control. Rigorous Lyapunov-based analysis is employed in order to ensure the stability of the controlled system. According to the information this paper has, this is by far the first model-free control method without any linearization operations for tower crane systems with uncertain dynamics, external disturbances, and control input constraints. The superior control performance and strong robustness of the designed control method was validated by a number of experimental results.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133212430","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

Measuring Method of Involute Profile Error Based on Machine Vision 基于机器视觉的渐开线轮廓误差测量方法

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517394

Zhi Shan, Meng Xin, Wu Di

{"title":"Measuring Method of Involute Profile Error Based on Machine Vision","authors":"Zhi Shan, Meng Xin, Wu Di","doi":"10.1109/RCAR52367.2021.9517394","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517394","url":null,"abstract":"To meet the requirement of fast on-line measurement of tooth profile error of medium and small modulus spur gear in automotive industry, a new algorithm for measuring involute tooth profile error based on machine vision with gear local image is proposed. The gray image of gear is acquired by gear visual measuring instrument, and the pixel information of transition zone of gear profile edge is extracted by Gauss filtering and threshold segmentation. The center of gear positioning is determined by fitting the circle based on fixed radius least square method with constraints. By extracting sub-pixel edge feature points of gear profile, a visual measurement model is constructed, and the measurement parameters, total deviation of involute profile and shape deviation of gear profile are calculated. The total tooth profile deviation of the tested gear measured by the method in this paper has reached 5-level accuracy. Compared with the result measured by M&M3525 NC Gear Measuring Center, the maximum measurement error of the total tooth profile deviation measured by the visual measuring instrument is $1mu mathrm{m}$, the maximum error of average measurement is less than $1mu mathrm{m}$. Experiments show that the measurement accuracy of the visual measurement system is equal to that of the gear measuring center, and it can meet the requirements of measuring the total tooth profile deviation of 5-level precision gear.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127724329","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

Optimization Design of Configuration, Structure and Drive Train Synthesis for Serial Robotic Arms 串联机械臂构型、结构及传动系综合优化设计

2021 IEEE International Conference on Real-time Computing and Robotics (RCAR) Pub Date : 2021-07-15 DOI: 10.1109/RCAR52367.2021.9517620

Jingchen Li, Jia Liu, Hongyu Ding, Yisen Hu, Jianxin Pang

{"title":"Optimization Design of Configuration, Structure and Drive Train Synthesis for Serial Robotic Arms","authors":"Jingchen Li, Jia Liu, Hongyu Ding, Yisen Hu, Jianxin Pang","doi":"10.1109/RCAR52367.2021.9517620","DOIUrl":"https://doi.org/10.1109/RCAR52367.2021.9517620","url":null,"abstract":"There have been various designs of collaborative robotic arms currently, and they have different advantages and disadvantages. Here, we propose a new method, by which one can optimally obtain a basic design of configuration, structure and drive train synthesis, based on the desired functions and performances. Specifically, we parameterize the configuration and drive train of robotic arms, simply assume the links as hollow cylinders, and parameterize the structural dimensions. These design parameters are linked to the mass, actuator selection, structural stiffness and workspace by a co-simulation model. Through using the optimization algorithm, a relatively optimal design for the desired functions and performances can be obtained. A design example demonstrates the application of the proposed approach in the optimal design of a lightweight six-degree-of-freedom robotic arm with the maximized workspace. Finally, we further analyze the workspace and illustrate the comparison between the optimal design and typical collaborative robotic arms. Our approach can be extended further for other particular design requirements.","PeriodicalId":232892,"journal":{"name":"2021 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127849783","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