Pub Date : 2023-08-06DOI: 10.1109/ICMA57826.2023.10216164
Yuzhe Zhu, M. Hirayama, Kimitoshi Yamazaki
In this study, we propose a novel end-effector for grasping and sorting operations on various parts of garments on a cutting machine in a factory. Furthermore, we propose a method for grasping a whole fabric by folding it back and forth into a smaller size, reducing the space required for packing and sorting various parts of multiple fabrics, reducing the height motion requirements of the robot, and increasing the ability to handle multiple types of clothing simultaneously. Then, we evaluated the proposed end-effector and the motion trajectory at a factory using real T-shirt parts of various materials, and confirmed the feasibility of the proposed end-effector and method for use in factories.
{"title":"An End-Effector with Winding and Scooping Functions for Handling Thin and Long Fabric Sheet","authors":"Yuzhe Zhu, M. Hirayama, Kimitoshi Yamazaki","doi":"10.1109/ICMA57826.2023.10216164","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216164","url":null,"abstract":"In this study, we propose a novel end-effector for grasping and sorting operations on various parts of garments on a cutting machine in a factory. Furthermore, we propose a method for grasping a whole fabric by folding it back and forth into a smaller size, reducing the space required for packing and sorting various parts of multiple fabrics, reducing the height motion requirements of the robot, and increasing the ability to handle multiple types of clothing simultaneously. Then, we evaluated the proposed end-effector and the motion trajectory at a factory using real T-shirt parts of various materials, and confirmed the feasibility of the proposed end-effector and method for use in factories.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114658533","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215770
Bozhuo Jiang
In order to design a rubber-roll rice husker the husker has been husking based on relevant literatures and its working principle has been determined. The forces of its main parts, such as the fast and slow rollers, have been analysed. Then, a design scheme of the whole husker has been determined. The specific design of grain separation mechanism, in the transmission aspect of the main design of the size of the belt wheel the number of belt roots, then according to the speed of the motor selection. In this paper, Solidworks was used to establish three-dimensional models CAD was used to describe parts drawings and other structures, and finally ANSYS Workbench was used to check the strength of spindle, cots and mecha.
{"title":"Structural Design of Rubber Roll Rice Huller","authors":"Bozhuo Jiang","doi":"10.1109/ICMA57826.2023.10215770","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215770","url":null,"abstract":"In order to design a rubber-roll rice husker the husker has been husking based on relevant literatures and its working principle has been determined. The forces of its main parts, such as the fast and slow rollers, have been analysed. Then, a design scheme of the whole husker has been determined. The specific design of grain separation mechanism, in the transmission aspect of the main design of the size of the belt wheel the number of belt roots, then according to the speed of the motor selection. In this paper, Solidworks was used to establish three-dimensional models CAD was used to describe parts drawings and other structures, and finally ANSYS Workbench was used to check the strength of spindle, cots and mecha.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116953145","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215775
X. Bo, Bai Jing, Zang Junbo
In recent years, the theory and methodology of integrated navigation system comprehensive evaluation have attracted much attention. Most of the existing parameter estimation methods are limited by the unknown prior information, and the integrated navigation state evaluation method also needs to evaluate the performance based on the external higher precision measurements. For integrated navigation, there are few studies on the effectiveness evaluation of filtering methods from the perspective of filtering process. This paper constructs an evaluation model of integrated navigation filtering algorithm, which combines projection pursuit technology. The best projection direction in projection pursuit technology is used to derive the weight of each filter performance index. In this paper, accelerated genetic algorithm is used to calculate the best projection direction. Finally, simulation experiments are carried out to simulate various navigation state simulation conditions, and the conventional Kalman filter and adaptive filter are compared. The conclusion of the simulation is that this method can be applied to the performance evaluation of the integrated navigation system fusion algorithm on the filtering mode.
{"title":"Online Evaluation Of The Effectiveness Of Combined Navigation Filtering Results And Study Of Parameter Availability","authors":"X. Bo, Bai Jing, Zang Junbo","doi":"10.1109/ICMA57826.2023.10215775","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215775","url":null,"abstract":"In recent years, the theory and methodology of integrated navigation system comprehensive evaluation have attracted much attention. Most of the existing parameter estimation methods are limited by the unknown prior information, and the integrated navigation state evaluation method also needs to evaluate the performance based on the external higher precision measurements. For integrated navigation, there are few studies on the effectiveness evaluation of filtering methods from the perspective of filtering process. This paper constructs an evaluation model of integrated navigation filtering algorithm, which combines projection pursuit technology. The best projection direction in projection pursuit technology is used to derive the weight of each filter performance index. In this paper, accelerated genetic algorithm is used to calculate the best projection direction. Finally, simulation experiments are carried out to simulate various navigation state simulation conditions, and the conventional Kalman filter and adaptive filter are compared. The conclusion of the simulation is that this method can be applied to the performance evaluation of the integrated navigation system fusion algorithm on the filtering mode.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117173918","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215899
Jianwei Liu, Enzeng Dong, Jigang Tong, Sen Yang, Shengzhi Du
Brain-computer interfaces (BCI) based on EEG have attracted extensive research and attention worldwide, while motor imagery (MI), mental arithmetic (MA), and P300 event-related potentials are a few of the more commonly used paradigms.Vision Transformer(ViT) is a new Transformer model that has superior global processing power compared to Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN).In this study, we propose a hybrid CNN-Transformer based model that uses CNN to convolve EEG signals in time and space, followed by ViT for global processing, and finally optimizes the model using 10-run $times 10$-fold cross-validation and validates it on a publicly available dataset of 29 subjects. Final accuracies of 87.23% and 90.79% were achieved on the MI and MA tasks, respectively. Compared to other literature, the model achieved higher classification accuracies.
{"title":"Classification of EEG signals based on CNN-Transformer model","authors":"Jianwei Liu, Enzeng Dong, Jigang Tong, Sen Yang, Shengzhi Du","doi":"10.1109/ICMA57826.2023.10215899","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215899","url":null,"abstract":"Brain-computer interfaces (BCI) based on EEG have attracted extensive research and attention worldwide, while motor imagery (MI), mental arithmetic (MA), and P300 event-related potentials are a few of the more commonly used paradigms.Vision Transformer(ViT) is a new Transformer model that has superior global processing power compared to Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN).In this study, we propose a hybrid CNN-Transformer based model that uses CNN to convolve EEG signals in time and space, followed by ViT for global processing, and finally optimizes the model using 10-run $times 10$-fold cross-validation and validates it on a publicly available dataset of 29 subjects. Final accuracies of 87.23% and 90.79% were achieved on the MI and MA tasks, respectively. Compared to other literature, the model achieved higher classification accuracies.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127284064","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10216012
Min Chen, Yihang Guo, Zhibo Geng, Lei Li
In order to improve the defect of high steady-state error of the algorithm caused by unsteady error signal noise in active noise control (ANC) system. The filtered-x least mean square/power normalized fourth (FXLMS/PF) algorithm is proposed by introducing the least mean square/fourth (LMS/F) algorithm into the ANC system and normalizing the power of the error signal in the algorithm. The algorithm is an improvement on the commonly used the filtered-x least mean square (FXLMS) algorithm and aims to balance noise reduction with fast convergence speed. The authors conducted simulations under different noise conditions, and the results demonstrated superior performance compared to other algorithms. The proposed algorithm offers a potential solution to the challenge of balancing noise reduction and convergence speed in ANC system.
{"title":"Filtered-x Least Mean Square/Power Normalized Fourth Algorithm (FXLMS/PF) for Active Noise Control","authors":"Min Chen, Yihang Guo, Zhibo Geng, Lei Li","doi":"10.1109/ICMA57826.2023.10216012","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216012","url":null,"abstract":"In order to improve the defect of high steady-state error of the algorithm caused by unsteady error signal noise in active noise control (ANC) system. The filtered-x least mean square/power normalized fourth (FXLMS/PF) algorithm is proposed by introducing the least mean square/fourth (LMS/F) algorithm into the ANC system and normalizing the power of the error signal in the algorithm. The algorithm is an improvement on the commonly used the filtered-x least mean square (FXLMS) algorithm and aims to balance noise reduction with fast convergence speed. The authors conducted simulations under different noise conditions, and the results demonstrated superior performance compared to other algorithms. The proposed algorithm offers a potential solution to the challenge of balancing noise reduction and convergence speed in ANC system.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127379800","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10216148
Yaling Tian, Yanlian Jiang, Xiaoyan Huang, Junjie Dan, Ji Li, Qiang Wang
In the process of automation and intelligent upgrading of manufacturing production lines in China, the application demand of lightweight robots with fewer degrees of free(DOF) in detecting and sorting stations has increased sharply. This paper takes the robot of the ligature box detecting and sorting station as the research object, analyzes the demand of the station for the robot, designs the 3-DOF lightweight robot arm based on this, adopts the homogeneous coordinates transformation analysis method, simplifies the way of establishing the coordinate system from the perspective of structure, determines the D-H parameters, and analyzes the forward and inverse kinematics of the robot arm; According to the designed structure, the geometric method is applied to solve the $theta$ 1, and according to the results of the forward kinematics, the analytical solution is used to solve the $theta$ 2 & $theta$ 3; Finally, workspace and kinematics parameters are studied in MATLAB. The results show that the designed robotic arm meets the requirements for detecting and sorting workspace.
{"title":"Research on Robot Technology with Fewer Degree of Free for Detecting and Sorting Station","authors":"Yaling Tian, Yanlian Jiang, Xiaoyan Huang, Junjie Dan, Ji Li, Qiang Wang","doi":"10.1109/ICMA57826.2023.10216148","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216148","url":null,"abstract":"In the process of automation and intelligent upgrading of manufacturing production lines in China, the application demand of lightweight robots with fewer degrees of free(DOF) in detecting and sorting stations has increased sharply. This paper takes the robot of the ligature box detecting and sorting station as the research object, analyzes the demand of the station for the robot, designs the 3-DOF lightweight robot arm based on this, adopts the homogeneous coordinates transformation analysis method, simplifies the way of establishing the coordinate system from the perspective of structure, determines the D-H parameters, and analyzes the forward and inverse kinematics of the robot arm; According to the designed structure, the geometric method is applied to solve the $theta$ 1, and according to the results of the forward kinematics, the analytical solution is used to solve the $theta$ 2 & $theta$ 3; Finally, workspace and kinematics parameters are studied in MATLAB. The results show that the designed robotic arm meets the requirements for detecting and sorting workspace.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125086520","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215860
Wenhua Li, Enzeng Dong, Jigang Tong, Sen Yang, Zufeng Zhang, Wenyu Li
Skeleton-based human action recognition has become a popular topic among researchers. This is because using skeletal data provides a robust solution to problems encountered in complex environments, such as changes in perspective and background interference. The robustness of skeletal data enables recognition methods to focus on more specific and relevant features. We propose a model called multilevel decomposition time aggregation graph convolution network (MDT-GCN), which utilizes a multilevel graph convolution kernel to capture higher-order spatial dependence relationships between joints. This is achieved by decomposing a human topology graph into smaller graphs, each of which has its own graph convolution kernel. To further enhance the performance of our model, we employ a two-flow framework and channel topology refinement strategy. Our experiments on the NTU-RGB+D60 and NTU-RGB+D120 datasets demonstrate that our MDT-GCN network outperforms the previous algorithm and significantly improves the accuracy of action recognition.
{"title":"Multilevel Decomposition Time Aggregation Graph Convolution Networks for Skeleton-Based Action Recognition","authors":"Wenhua Li, Enzeng Dong, Jigang Tong, Sen Yang, Zufeng Zhang, Wenyu Li","doi":"10.1109/ICMA57826.2023.10215860","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215860","url":null,"abstract":"Skeleton-based human action recognition has become a popular topic among researchers. This is because using skeletal data provides a robust solution to problems encountered in complex environments, such as changes in perspective and background interference. The robustness of skeletal data enables recognition methods to focus on more specific and relevant features. We propose a model called multilevel decomposition time aggregation graph convolution network (MDT-GCN), which utilizes a multilevel graph convolution kernel to capture higher-order spatial dependence relationships between joints. This is achieved by decomposing a human topology graph into smaller graphs, each of which has its own graph convolution kernel. To further enhance the performance of our model, we employ a two-flow framework and channel topology refinement strategy. Our experiments on the NTU-RGB+D60 and NTU-RGB+D120 datasets demonstrate that our MDT-GCN network outperforms the previous algorithm and significantly improves the accuracy of action recognition.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126149169","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10215607
Guoxin Qu, Litao Zhang, Xige Zhang
An adaptive fixed-time control method is proposed for reusable launch vehicles (RLV) subject to full state constraints, input saturation, dynamic coupling, parameter uncertainty and disturbance. By using the back-stepping control technique, an integrated adaptive fixed-time control law is designed, which combines the tan barrier Lyapunov function (BLF) to deal with the full-state constraints. At the same time, parameter uncertainty, unknown dynamic coupling, and perturbations are effectively attenuated by using adaptive estimation techniques and the designed saturation compensator effectively reduces the adverse effects caused by input saturation. Finally, six-degree-of-freedom simulation proves the advantages and effectiveness of the designed adaptive fixed-time control method.
{"title":"Adaptive Fixed-Time Attitude Tracking Control in Reentry Phase for Reusable Launch Vehicle","authors":"Guoxin Qu, Litao Zhang, Xige Zhang","doi":"10.1109/ICMA57826.2023.10215607","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10215607","url":null,"abstract":"An adaptive fixed-time control method is proposed for reusable launch vehicles (RLV) subject to full state constraints, input saturation, dynamic coupling, parameter uncertainty and disturbance. By using the back-stepping control technique, an integrated adaptive fixed-time control law is designed, which combines the tan barrier Lyapunov function (BLF) to deal with the full-state constraints. At the same time, parameter uncertainty, unknown dynamic coupling, and perturbations are effectively attenuated by using adaptive estimation techniques and the designed saturation compensator effectively reduces the adverse effects caused by input saturation. Finally, six-degree-of-freedom simulation proves the advantages and effectiveness of the designed adaptive fixed-time control method.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123336261","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 : 2023-08-06DOI: 10.1109/ICMA57826.2023.10216082
Zicheng Dong, Hui Shao, H. Huang
Traditional impedance control is a simple and valid way for robot force tracking, but the uncertainty of the contact environment can seriously interfere with tracking accuracy. In this paper, we present a novel reinforcement learning variable impedance scheme based on PILCO algorithm, which trains a RBF policy network that dynamically adjusts the damping coefficient to compensate for environment uncertainty. Considering the randomness of environment and learning efficiency, a contact state transition model is established by Gaussian process regression, which can be used for state prediction and policy evaluation. The policy is then updated by a gradient-based approach. The simulation study indicates that our robot only takes 18 interactions with an unknown environment to learn an optimal variable impedance policy, which can be applied to various unknown contact environments and has better control accuracy than traditional methods.
{"title":"Variable Impedance Control for Force Tracking Based on PILCO in Uncertain Environment","authors":"Zicheng Dong, Hui Shao, H. Huang","doi":"10.1109/ICMA57826.2023.10216082","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216082","url":null,"abstract":"Traditional impedance control is a simple and valid way for robot force tracking, but the uncertainty of the contact environment can seriously interfere with tracking accuracy. In this paper, we present a novel reinforcement learning variable impedance scheme based on PILCO algorithm, which trains a RBF policy network that dynamically adjusts the damping coefficient to compensate for environment uncertainty. Considering the randomness of environment and learning efficiency, a contact state transition model is established by Gaussian process regression, which can be used for state prediction and policy evaluation. The policy is then updated by a gradient-based approach. The simulation study indicates that our robot only takes 18 interactions with an unknown environment to learn an optimal variable impedance policy, which can be applied to various unknown contact environments and has better control accuracy than traditional methods.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123714083","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}
Visuotactile simulation is crucial for robot dexterous manipulation skill learning, but remains a challenging problem. Most of the existing methods are designed for GelSight-type sensors, which focus on optical response simulation and do not pay much attention to the contact dynamics of elastomer. In this paper, we propose a high-fidelity tactile imprint simulation model of the visuotactile sensors, which uses finite element analysis (FEM) to simulate realistic contact dynamics. Moreover, a vertex mapping-based rendering method is proposed to realize real-time textured tactile imprint rendering using finite element results, which can be further used to extract tactile features, such as markers motion field. In order to achieve high-fidelity simulation effects, we also design a simulation parameter calibration method, which calibrates the finite element parameters of the elastomer simulation by optimizing the mean square error of the distance from the corresponding markers of the contact area (Marker-MSE) between the real and simulated elastomer deformation. Furthermore, a large number of quantitative and qualitative simulated contact experiments are performed, and the results strong verity the effectiveness and robustness of the proposed simulation model. This study is an active exploration of the simulation of GelStereo-type sensors, and it has positive significance for the simulation modeling of visuotactile sensors that focus on contact dynamics and textured imprints.
{"title":"Tactile Imprint Simulation of GelStereo Visuotactile Sensors","authors":"Shaowei Cui, Yu Wang, Shuo Wang, Qian Li, Rui Wang, Chaofan Zhang","doi":"10.1109/ICMA57826.2023.10216245","DOIUrl":"https://doi.org/10.1109/ICMA57826.2023.10216245","url":null,"abstract":"Visuotactile simulation is crucial for robot dexterous manipulation skill learning, but remains a challenging problem. Most of the existing methods are designed for GelSight-type sensors, which focus on optical response simulation and do not pay much attention to the contact dynamics of elastomer. In this paper, we propose a high-fidelity tactile imprint simulation model of the visuotactile sensors, which uses finite element analysis (FEM) to simulate realistic contact dynamics. Moreover, a vertex mapping-based rendering method is proposed to realize real-time textured tactile imprint rendering using finite element results, which can be further used to extract tactile features, such as markers motion field. In order to achieve high-fidelity simulation effects, we also design a simulation parameter calibration method, which calibrates the finite element parameters of the elastomer simulation by optimizing the mean square error of the distance from the corresponding markers of the contact area (Marker-MSE) between the real and simulated elastomer deformation. Furthermore, a large number of quantitative and qualitative simulated contact experiments are performed, and the results strong verity the effectiveness and robustness of the proposed simulation model. This study is an active exploration of the simulation of GelStereo-type sensors, and it has positive significance for the simulation modeling of visuotactile sensors that focus on contact dynamics and textured imprints.","PeriodicalId":151364,"journal":{"name":"2023 IEEE International Conference on Mechatronics and Automation (ICMA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125505871","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：