Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907062
Guang Feng, Jiaji Zhang, G. Chai, Maoqin Li, Guokun Zuo, Lei Yang
Visual and haptic feedback are crucial to enhance the effectiveness of robot-assisted rehabilitation. To improve the performance of clinical rehabilitation training for patients with motor dysfunction, we propose an effective training strategy based on visual and haptic feedback. Haptic feedback is generated by a designed artificial potential field, which allows patients to perceive the correct training direction. The effectiveness of the proposed training strategy is initially verified, by recruiting three healthy subjects to perform circle drawing tasks on an upper limb rehabilitation robot. Experimental results showed that higher training accuracies were obtained using visual-haptic feedback compared to those with unimodal feedback. The proposed strategy can enhance the users' perception of the training process and corrects the incorrect movements in real-time, simultaneously. The current training strategy can be applied to commercial rehabilitation robots and meet the rehabilitation training needs of the users with impaired vision or the vision is unavailable.
{"title":"An Effective Training Strategy for Upper-limb Rehabilitation Robots Based on Visual-haptic Feedback Using Potential Field","authors":"Guang Feng, Jiaji Zhang, G. Chai, Maoqin Li, Guokun Zuo, Lei Yang","doi":"10.1109/CYBER55403.2022.9907062","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907062","url":null,"abstract":"Visual and haptic feedback are crucial to enhance the effectiveness of robot-assisted rehabilitation. To improve the performance of clinical rehabilitation training for patients with motor dysfunction, we propose an effective training strategy based on visual and haptic feedback. Haptic feedback is generated by a designed artificial potential field, which allows patients to perceive the correct training direction. The effectiveness of the proposed training strategy is initially verified, by recruiting three healthy subjects to perform circle drawing tasks on an upper limb rehabilitation robot. Experimental results showed that higher training accuracies were obtained using visual-haptic feedback compared to those with unimodal feedback. The proposed strategy can enhance the users' perception of the training process and corrects the incorrect movements in real-time, simultaneously. The current training strategy can be applied to commercial rehabilitation robots and meet the rehabilitation training needs of the users with impaired vision or the vision is unavailable.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"31 1","pages":"678-681"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81078178","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}
Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907340
Guoyu Zuo, Yan Liu, Gao Huang, Daoxiong Gong
The challenge in image-based visual servoing is to deal with the visibility constraints, which require the image features to always remain in the field of view (FOV) of the camera. In this paper, a novel constraint function is proposed to address this problem. The FOV constraint function represented by the coordinates of the features and the region boundaries defined in the image is added to the classical proportional controller, which leads the image features from the margin to the center of the image. Simulation results verify the efficiency of the modified controller by controlling a robot manipulator with eye-in-hand configuration.
{"title":"Image-Based Visual Servoing under Field of View Constraints for Robot Manipulators*","authors":"Guoyu Zuo, Yan Liu, Gao Huang, Daoxiong Gong","doi":"10.1109/CYBER55403.2022.9907340","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907340","url":null,"abstract":"The challenge in image-based visual servoing is to deal with the visibility constraints, which require the image features to always remain in the field of view (FOV) of the camera. In this paper, a novel constraint function is proposed to address this problem. The FOV constraint function represented by the coordinates of the features and the region boundaries defined in the image is added to the classical proportional controller, which leads the image features from the margin to the center of the image. Simulation results verify the efficiency of the modified controller by controlling a robot manipulator with eye-in-hand configuration.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"62 1","pages":"77-82"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73899073","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}
This paper compares two methods of sensory feedback (SF) in prosthetic hands noninvasively by investigating practical experiments, a questionnaire form, and brain activity mapping. The modality-missed-matched sensory feedback (MMM-SF) is per-formed on remnant muscles of the amputated limb using transcutaneous electrical Stimulation (TES). In addition, an armband with multi-modal sensory stimulators is being used for the modality-matched sensory feedback (MM-SF) on the superficial layer of the skin. Both sensory stimulators have been synced with a designed myoelectric bionic hand, equipped with differ-ent sensors to assess surrounding stimuli. The results indicate that the MMM-SF imposes higher cognitive loads on amputee participants than the MM-SF strat-egy. Furthermore, the effects of sensory stimulation by proposed methods have been investigated by brain mapping through quantitative electroencephalography (QEEG) and low-resolution brain electromagnetic to-mography (LORETA), which shows that perceived SF in both approaches could assist in recovering the Alpha/Delta-band rhythm balance.
{"title":"A Comparison of Modality-Matched and Modality-Missed-Matched Sensory Feedback by Brain Mapping and Practical Trials","authors":"Saeed Bahrami Moqadam, Ahmad Saleh Asheghabadi, Farzaneh Norouzi, Nikki Akraminejad, Behruz Shiee Zadeh Yazdi, Jing Xu","doi":"10.1109/CYBER55403.2022.9907057","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907057","url":null,"abstract":"This paper compares two methods of sensory feedback (SF) in prosthetic hands noninvasively by investigating practical experiments, a questionnaire form, and brain activity mapping. The modality-missed-matched sensory feedback (MMM-SF) is per-formed on remnant muscles of the amputated limb using transcutaneous electrical Stimulation (TES). In addition, an armband with multi-modal sensory stimulators is being used for the modality-matched sensory feedback (MM-SF) on the superficial layer of the skin. Both sensory stimulators have been synced with a designed myoelectric bionic hand, equipped with differ-ent sensors to assess surrounding stimuli. The results indicate that the MMM-SF imposes higher cognitive loads on amputee participants than the MM-SF strat-egy. Furthermore, the effects of sensory stimulation by proposed methods have been investigated by brain mapping through quantitative electroencephalography (QEEG) and low-resolution brain electromagnetic to-mography (LORETA), which shows that perceived SF in both approaches could assist in recovering the Alpha/Delta-band rhythm balance.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"47 5 1","pages":"498-503"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73013450","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}
Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907246
Lina Hao, Zhe Li, Shuai Wang, Chenling Hao
The unmanned combat game platform is the technical carrier to research unmanned combat issues. Although most current unmanned combat simulation platforms can effectively simulate the unmanned combat process, their scenes are fixed and single. They cannot carry out the secondary design of the scene. At the same time, they also lack an effective description of the scene information. Therefore, this paper takes air-ground unmanned combat as a specific task scenario and independently develops an unmanned combat deduction platform based on the Hybrid Stochastic Time Delay Petri Net (HSTPN) modelling theory and PyQt development tool. The platform supports scene modelling and model changes, deep reinforcement learning algorithm battles, animation deductions, file storage, etc. At the same time, a battle decision algorithm is designed based on Proximal Policy Optimization (PPO). The experimental results show that the unmanned combat game platform can fully realize the combat process simulation. Its scene modelling function can show all the hybrid characteristics of the combat process and support the modification of the scene model and its secondary development. The battle function can complete the confrontation game of the decision-making algorithm.
{"title":"Design and Development of Unmanned Combat Game Platform","authors":"Lina Hao, Zhe Li, Shuai Wang, Chenling Hao","doi":"10.1109/CYBER55403.2022.9907246","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907246","url":null,"abstract":"The unmanned combat game platform is the technical carrier to research unmanned combat issues. Although most current unmanned combat simulation platforms can effectively simulate the unmanned combat process, their scenes are fixed and single. They cannot carry out the secondary design of the scene. At the same time, they also lack an effective description of the scene information. Therefore, this paper takes air-ground unmanned combat as a specific task scenario and independently develops an unmanned combat deduction platform based on the Hybrid Stochastic Time Delay Petri Net (HSTPN) modelling theory and PyQt development tool. The platform supports scene modelling and model changes, deep reinforcement learning algorithm battles, animation deductions, file storage, etc. At the same time, a battle decision algorithm is designed based on Proximal Policy Optimization (PPO). The experimental results show that the unmanned combat game platform can fully realize the combat process simulation. Its scene modelling function can show all the hybrid characteristics of the combat process and support the modification of the scene model and its secondary development. The battle function can complete the confrontation game of the decision-making algorithm.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"11 1","pages":"1032-1037"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74847213","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}
Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907123
Wenjun Zhang, Dong Ma, Jingxuan Gao, Teng Ma, Yueyang Ben
The underwater terrain-aid navigation (TAN) method using a single-beam sonar has demonstrated its potential for autonomous underwater vehicles (AUVs) long-range accurate navigation without the aid of acoustics arrays and satellites. This paper proposed a robust terrain contour aid navigation(TCAN) method using a single-beam sonar in the smooth terrain areas, which considered the error characteristics of an inertial navigation system(INS), can realize long-range underwater navigation. As for the measurement error of a single-beam sonar and the influence of the smooth terrain areas, this paper proposed a measurement confidence interval calculation method, which can reduce the influence of the measurement error on the navigational result, improving the accuracy and robustness of the TCAN method. The influence of algorithm parameters on the result of the navigation method are researched by simulation experiments. The results show that the navigation method can realize long-range underwater navigation in the smooth terrain areas on making full use of an INS error characteristics, and has a good application prospect.
{"title":"A Robust Seabed Terrain Contour Aid Navigation Method Facing the Smooth Terrain","authors":"Wenjun Zhang, Dong Ma, Jingxuan Gao, Teng Ma, Yueyang Ben","doi":"10.1109/CYBER55403.2022.9907123","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907123","url":null,"abstract":"The underwater terrain-aid navigation (TAN) method using a single-beam sonar has demonstrated its potential for autonomous underwater vehicles (AUVs) long-range accurate navigation without the aid of acoustics arrays and satellites. This paper proposed a robust terrain contour aid navigation(TCAN) method using a single-beam sonar in the smooth terrain areas, which considered the error characteristics of an inertial navigation system(INS), can realize long-range underwater navigation. As for the measurement error of a single-beam sonar and the influence of the smooth terrain areas, this paper proposed a measurement confidence interval calculation method, which can reduce the influence of the measurement error on the navigational result, improving the accuracy and robustness of the TCAN method. The influence of algorithm parameters on the result of the navigation method are researched by simulation experiments. The results show that the navigation method can realize long-range underwater navigation in the smooth terrain areas on making full use of an INS error characteristics, and has a good application prospect.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"29 1","pages":"1166-1170"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75058972","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}
Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907573
Xiaoliang Fan, Jin Sui, Naifeng He, Bi Zhang, Chunguang Bu, Junbo Yang, Lele Cui
Classical PID controllers usually rely on some prior knowledge to manually adjust the gains of the controller and determine them. However, when the mobile robot works in a complex and changeable environment, the fixed PID gains may be difficult to meet the needs of the robot trajectory tracking accuracy. Therefore, this paper proposes a Q-learning-based adaptive PID trajectory tracking algorithm. Firstly, we construct a trajectory tracking Q-PID controller based on the error model of mobile robot. Then, the Q-learning algorithm is used to adaptively adjust the gains of the PID controller online. Meanwhile, the incremental active learning exploration method is used to improve learning efficiency and adaptability of agent. Finally, we use simulation experiments to verify the high performance of our algorithm.
{"title":"Adaptive PID Trajectory Tracking Algorithm Using Q-Learning for Mobile Robots","authors":"Xiaoliang Fan, Jin Sui, Naifeng He, Bi Zhang, Chunguang Bu, Junbo Yang, Lele Cui","doi":"10.1109/CYBER55403.2022.9907573","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907573","url":null,"abstract":"Classical PID controllers usually rely on some prior knowledge to manually adjust the gains of the controller and determine them. However, when the mobile robot works in a complex and changeable environment, the fixed PID gains may be difficult to meet the needs of the robot trajectory tracking accuracy. Therefore, this paper proposes a Q-learning-based adaptive PID trajectory tracking algorithm. Firstly, we construct a trajectory tracking Q-PID controller based on the error model of mobile robot. Then, the Q-learning algorithm is used to adaptively adjust the gains of the PID controller online. Meanwhile, the incremental active learning exploration method is used to improve learning efficiency and adaptability of agent. Finally, we use simulation experiments to verify the high performance of our algorithm.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"21 1","pages":"1112-1117"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82814100","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}
Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907578
Songna Zhang, Tong Jia, Wenhao Li, Xiaojun Sun
The 3D reconstruction technology of indoor scenes based on image sequences has always been the focus of research in computer vision. It can be widely used in medical diagnosis, unmanned driving, AR/VR, cultural relics restoration, and other fields. However, due to the complex information and cluttered features of indoor scenes, the existing feature matching algorithms and point cloud registration algorithms still have certain limitations in terms of computational efficiency and matching accuracy. Therefore, this paper firstly adopts a uniform extraction of ORB features method based on octree and a feature matching method based on colour and descriptor distance information and uses the RANSAC algorithm to eliminate mismatched points to obtain matching results with high accuracy. Secondly, this paper adopts a point cloud fine-registration method based on a double threshold constraint. Based on the point cloud normal vector angle threshold constraint, the search of the nearest neighbour point pair in the ICP algorithm is realized through the adaptive distance threshold constraint. Finally, experimental analysis is carried out in a real indoor scene to verify the effectiveness of the proposed algorithm in reconstruction efficiency and accuracy.
{"title":"A 3D Reconstruction Technology of Indoor Scene based on Image Sequence","authors":"Songna Zhang, Tong Jia, Wenhao Li, Xiaojun Sun","doi":"10.1109/CYBER55403.2022.9907578","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907578","url":null,"abstract":"The 3D reconstruction technology of indoor scenes based on image sequences has always been the focus of research in computer vision. It can be widely used in medical diagnosis, unmanned driving, AR/VR, cultural relics restoration, and other fields. However, due to the complex information and cluttered features of indoor scenes, the existing feature matching algorithms and point cloud registration algorithms still have certain limitations in terms of computational efficiency and matching accuracy. Therefore, this paper firstly adopts a uniform extraction of ORB features method based on octree and a feature matching method based on colour and descriptor distance information and uses the RANSAC algorithm to eliminate mismatched points to obtain matching results with high accuracy. Secondly, this paper adopts a point cloud fine-registration method based on a double threshold constraint. Based on the point cloud normal vector angle threshold constraint, the search of the nearest neighbour point pair in the ICP algorithm is realized through the adaptive distance threshold constraint. Finally, experimental analysis is carried out in a real indoor scene to verify the effectiveness of the proposed algorithm in reconstruction efficiency and accuracy.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"15 1","pages":"906-911"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88273516","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}
Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907032
Jiangeng Li, Hong Liu, Gao Huang, Guoyu Zuo
6D pose estimation is widely used in robot tasks such as sorting and grasping. RGB-D-based methods have recently attained brilliant success, but they are still susceptible to heavy occlusion. Our critical insight is that color and geometry information in RGBD images are two complementary data, and the crux of the pose estimation problem under occlusion is fully leveraging them. Towards this end, we propose a new color and geometry feature fusion module that can efficiently leverage two complementary data sources from RGB-D images. Unlike prior fusion methods, we conduct a two-stage fusion strategy to do color-depth fusion and local-global fusion successively. Specifically, we fuse the color features extracted from RGB images into the point cloud in the first stage. In the second stage, we extract local and global features from the fused point cloud using an ASSANet-like network and splice them together to obtain the final fusion features. We conducted experiments on the widely used LineMod and YCB-Video datasets, which shows that our method improves the prediction accuracy while reducing the training time.
{"title":"An Efficient Color and Geometric Feature Fusion Module for 6D Object Pose Estiamtion","authors":"Jiangeng Li, Hong Liu, Gao Huang, Guoyu Zuo","doi":"10.1109/CYBER55403.2022.9907032","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907032","url":null,"abstract":"6D pose estimation is widely used in robot tasks such as sorting and grasping. RGB-D-based methods have recently attained brilliant success, but they are still susceptible to heavy occlusion. Our critical insight is that color and geometry information in RGBD images are two complementary data, and the crux of the pose estimation problem under occlusion is fully leveraging them. Towards this end, we propose a new color and geometry feature fusion module that can efficiently leverage two complementary data sources from RGB-D images. Unlike prior fusion methods, we conduct a two-stage fusion strategy to do color-depth fusion and local-global fusion successively. Specifically, we fuse the color features extracted from RGB images into the point cloud in the first stage. In the second stage, we extract local and global features from the fused point cloud using an ASSANet-like network and splice them together to obtain the final fusion features. We conducted experiments on the widely used LineMod and YCB-Video datasets, which shows that our method improves the prediction accuracy while reducing the training time.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"23 1","pages":"83-88"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74599402","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}
Droplet actuation simplifies the handling of various reagents or samples and can be applied to a wide range of fields, including chemistry, biology, biomedical, and others. This paper presents a programmable droplet control system based on a magnetoelastic membrane and electromagnetic pillar array. Different magnetic blocks with different magnetization directions were designed on the silicone rubber membrane, and the magnetoelastic membrane deformed under the magnetic field generated by the array of electromagnetic pillars. By combining the gravitational forces of the droplet and the deformation of the magnetic membranes, the motion of the droplet can be controlled. Furthermore, the surface of membranes was ablated with a laser machine to impart superhydrophobic properties. The simulation results show that with the different magnetic fields, the droplet can move lengthwise, widthwise, and diagonally in the horizontal plane, and multiple droplets can be merged and mixed. In contrast to the traditional droplet control method, the droplet programmable movement control system utilizing superhydrophobic magnetoelastic membranes and an electromagnetic pillar array has better stationarity, flexibility and does not affect the basic properties of the droplets.
{"title":"Design of Programmable Droplet Manipulation Platform Based on Magnetic Control","authors":"Xianmiao Zhang, Jie Liu, Jiying Liu, Yu-zhou Wang, Mian Zhang, Hongbiao Xiang","doi":"10.1109/CYBER55403.2022.9907625","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907625","url":null,"abstract":"Droplet actuation simplifies the handling of various reagents or samples and can be applied to a wide range of fields, including chemistry, biology, biomedical, and others. This paper presents a programmable droplet control system based on a magnetoelastic membrane and electromagnetic pillar array. Different magnetic blocks with different magnetization directions were designed on the silicone rubber membrane, and the magnetoelastic membrane deformed under the magnetic field generated by the array of electromagnetic pillars. By combining the gravitational forces of the droplet and the deformation of the magnetic membranes, the motion of the droplet can be controlled. Furthermore, the surface of membranes was ablated with a laser machine to impart superhydrophobic properties. The simulation results show that with the different magnetic fields, the droplet can move lengthwise, widthwise, and diagonally in the horizontal plane, and multiple droplets can be merged and mixed. In contrast to the traditional droplet control method, the droplet programmable movement control system utilizing superhydrophobic magnetoelastic membranes and an electromagnetic pillar array has better stationarity, flexibility and does not affect the basic properties of the droplets.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"21 1","pages":"1224-1229"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74911572","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}
Pub Date : 2022-07-27DOI: 10.1109/CYBER55403.2022.9907262
Yunfeng Bai, Fengming Li, Man Zhao, Wei Wang, Yibin Li, R. Song
This paper proposes a robot automatic valve turning control strategy based on teaching learning, which consists of teaching, model learning and task repetition. The first stage is the teaching and learning stage. The robot learns motor skills by observing the human performing tasks. In order to accurately learn motor skills from demonstrations, data alignment is performed on the teaching data through Dynamic Time Warping (DTW). The second stage is the model construction and learning stage. The high-level learning strategy aims to learn motor skills from demonstrations through Dynamic Movement Primitives (DMP), using the statistical approach Gaussian Mixture Model and Gaussian Mixture Regression (GMM-GMR) to analyze the data from demonstrations. And the valve turning is repetition. To verify the effectiveness of the proposed control strategy, the experiment of the butterfly valve closing is performed. The results show that the robot is able to learn and reproduce the valve reaching and turning tasks. It completes the valve closing action by turning the valve for 7 turns.
本文提出了一种基于教与学的机器人自动转阀控制策略，该策略由教学、模型学习和任务重复组成。第一阶段是教与学阶段。机器人通过观察人类执行任务来学习运动技能。为了从演示中准确地学习运动技能，通过动态时间翘曲(Dynamic Time Warping, DTW)对教学数据进行数据对齐。第二阶段是模式建构和学习阶段。高阶学习策略旨在通过动态运动原语(Dynamic Movement Primitives, DMP)从演示中学习运动技能，使用统计方法高斯混合模型和高斯混合回归(Gaussian Mixture Model, GMM-GMR)对演示数据进行分析。阀门转动是重复的。为了验证所提控制策略的有效性，进行了蝶阀关闭实验。结果表明，该机器人能够学习和再现阀门到达和转向任务。通过转动阀门7圈完成阀门关闭动作。
{"title":"Robot Manipulation Skill Learning Based on Dynamic Movement Primitive*","authors":"Yunfeng Bai, Fengming Li, Man Zhao, Wei Wang, Yibin Li, R. Song","doi":"10.1109/CYBER55403.2022.9907262","DOIUrl":"https://doi.org/10.1109/CYBER55403.2022.9907262","url":null,"abstract":"This paper proposes a robot automatic valve turning control strategy based on teaching learning, which consists of teaching, model learning and task repetition. The first stage is the teaching and learning stage. The robot learns motor skills by observing the human performing tasks. In order to accurately learn motor skills from demonstrations, data alignment is performed on the teaching data through Dynamic Time Warping (DTW). The second stage is the model construction and learning stage. The high-level learning strategy aims to learn motor skills from demonstrations through Dynamic Movement Primitives (DMP), using the statistical approach Gaussian Mixture Model and Gaussian Mixture Regression (GMM-GMR) to analyze the data from demonstrations. And the valve turning is repetition. To verify the effectiveness of the proposed control strategy, the experiment of the butterfly valve closing is performed. The results show that the robot is able to learn and reproduce the valve reaching and turning tasks. It completes the valve closing action by turning the valve for 7 turns.","PeriodicalId":34110,"journal":{"name":"IET Cybersystems and Robotics","volume":"67 1","pages":"579-584"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76529737","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：