Pub Date : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011959
Yujian Zhang, Yuan Liu, Shiyin Qiu, Fengrui Ji, Jinze Wei, Dong Ming
Motor imagery-based brain-computer interfaces (MI-BCI) help patients to reconstruct damaged neural path-ways in the field of neurorehabilitation. However, difficulties in performing abstract imagery tasks and generating discriminable EEG signals for some subjects limit the application of MI-BCI, and the devices required for the visual guidance paradigm are not portable in MI-BCI application scenarios for wearable robotic systems. In this study, we propose an enhanced motor imagery paradigm combining sequential elec-trical stimulation (SES) encoded by gait phase with a gait motor imagery (MI) task, guiding subjects to perform MI task with task-mapped electrical stimulation (ES). The goal of the novel paradigm is to reduce the difficulty of lower limbs MI task and to improve the performance of the MI-BCI by combining movement and sensation. We conducted comparison experiments on eight healthy subjects, and the MI task in the SES-Stim paradigm achieved greater activation of motor cortex in the $alpha$ and $beta$ rhythm, and the proposed SES-Stim paradigm could improve the classification performance.
{"title":"Enhanced Motor Imagery of Lower Limbs Induced by Gait Phase Encoding Sensory Electrical Stimulation","authors":"Yujian Zhang, Yuan Liu, Shiyin Qiu, Fengrui Ji, Jinze Wei, Dong Ming","doi":"10.1109/ROBIO55434.2022.10011959","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011959","url":null,"abstract":"Motor imagery-based brain-computer interfaces (MI-BCI) help patients to reconstruct damaged neural path-ways in the field of neurorehabilitation. However, difficulties in performing abstract imagery tasks and generating discriminable EEG signals for some subjects limit the application of MI-BCI, and the devices required for the visual guidance paradigm are not portable in MI-BCI application scenarios for wearable robotic systems. In this study, we propose an enhanced motor imagery paradigm combining sequential elec-trical stimulation (SES) encoded by gait phase with a gait motor imagery (MI) task, guiding subjects to perform MI task with task-mapped electrical stimulation (ES). The goal of the novel paradigm is to reduce the difficulty of lower limbs MI task and to improve the performance of the MI-BCI by combining movement and sensation. We conducted comparison experiments on eight healthy subjects, and the MI task in the SES-Stim paradigm achieved greater activation of motor cortex in the $alpha$ and $beta$ rhythm, and the proposed SES-Stim paradigm could improve the classification performance.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125524575","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011825
Yaling Pan, Li He, Y. Guan, Hong Zhang
Local feature descriptors play a crucial role in computer vision problems, especially robot motion. Existing descriptors are highly accurate, but their performance de-pends on the influence of distracting factors, such as illumi-nation and viewpoint. There is room for further improvement of these descriptors. In this paper, we provide an in-depth analysis of several exciting features of the descriptor fusion model (DFM) we have proposed in our recent work, which uses an autoencoder to combine descriptors and exploit their respective advantages. With this DFM framework, we fur-ther validate that fused descriptors can retain advantageous properties and that our DFM is a generally applicable method with respect to various component descriptors. Specifically, we evaluate multiple combinations of hand-crafted and CNN descriptors concerning their performance on a benchmark dataset with illumination and viewpoint changes to obtain comprehensive experimental results. The results show that the fused descriptors have better matching accuracy than their component descriptors.
{"title":"An Experimental Study of Keypoint Descriptor Fusion","authors":"Yaling Pan, Li He, Y. Guan, Hong Zhang","doi":"10.1109/ROBIO55434.2022.10011825","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011825","url":null,"abstract":"Local feature descriptors play a crucial role in computer vision problems, especially robot motion. Existing descriptors are highly accurate, but their performance de-pends on the influence of distracting factors, such as illumi-nation and viewpoint. There is room for further improvement of these descriptors. In this paper, we provide an in-depth analysis of several exciting features of the descriptor fusion model (DFM) we have proposed in our recent work, which uses an autoencoder to combine descriptors and exploit their respective advantages. With this DFM framework, we fur-ther validate that fused descriptors can retain advantageous properties and that our DFM is a generally applicable method with respect to various component descriptors. Specifically, we evaluate multiple combinations of hand-crafted and CNN descriptors concerning their performance on a benchmark dataset with illumination and viewpoint changes to obtain comprehensive experimental results. The results show that the fused descriptors have better matching accuracy than their component descriptors.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121306997","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011794
Lei Zhang, Kaixin Bai, Zhaopeng Chen, Yunlei Shi, Jianwei Zhang
Precise robotic grasping of several novel objects is a huge challenge in manufacturing, automation, and logistics. Most of the current methods for model-free grasping are disadvantaged by the sparse data in grasping datasets and by errors in sensor data and contact models. This study combines data generation and sim - to- real transfer learning in a grasping framework that reduces the sim-to-real gap and enables precise and reliable model-free grasping. A large-scale robotic grasping dataset with dense grasp labels is generated using domain randomization methods and a novel data augmentation method for deep learning-based robotic grasping to solve data sparse problem. We present an end-to-end robotic grasping network with a grasp optimizer. The grasp policies are trained with sim-to-real transfer learning. The presented results suggest that our grasping framework reduces the uncertainties in grasping datasets, sensor data, and contact models. In physical robotic experiments, our grasping framework grasped single known objects and novel complex-shaped household objects with a success rate of 90.91%. In a complex scenario with multi-objects robotic grasping, the success rate was 85.71%. The proposed grasping framework outperformed two state-of-the-art methods in both known and unknown object robotic grasping.
{"title":"Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning","authors":"Lei Zhang, Kaixin Bai, Zhaopeng Chen, Yunlei Shi, Jianwei Zhang","doi":"10.1109/ROBIO55434.2022.10011794","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011794","url":null,"abstract":"Precise robotic grasping of several novel objects is a huge challenge in manufacturing, automation, and logistics. Most of the current methods for model-free grasping are disadvantaged by the sparse data in grasping datasets and by errors in sensor data and contact models. This study combines data generation and sim - to- real transfer learning in a grasping framework that reduces the sim-to-real gap and enables precise and reliable model-free grasping. A large-scale robotic grasping dataset with dense grasp labels is generated using domain randomization methods and a novel data augmentation method for deep learning-based robotic grasping to solve data sparse problem. We present an end-to-end robotic grasping network with a grasp optimizer. The grasp policies are trained with sim-to-real transfer learning. The presented results suggest that our grasping framework reduces the uncertainties in grasping datasets, sensor data, and contact models. In physical robotic experiments, our grasping framework grasped single known objects and novel complex-shaped household objects with a success rate of 90.91%. In a complex scenario with multi-objects robotic grasping, the success rate was 85.71%. The proposed grasping framework outperformed two state-of-the-art methods in both known and unknown object robotic grasping.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121652778","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011803
Simon Harms, Tomohiro Kawano, K. Nagaoka
A climbing robot for lunar caves and craters, called a tethered-climbing robot, is proposed. It consists of a robotic platform with a robotic arm which is suspended via tethers from multiple grippers. It achieves spatial climbing locomotion by relocating the grippers with the arm and by controlling the length of the tethers. In this paper, the kinematics and statics of a tethered-climbing robot are derived, and a method to calculate the workspace of the extendable arm is introduced. Furthermore, the gait and workspace of a generic tethered-climbing robot under lunar gravity are analyzed.
{"title":"A Tethered-Climbing Robot System for Lunar Terrain: Modeling and Analysis","authors":"Simon Harms, Tomohiro Kawano, K. Nagaoka","doi":"10.1109/ROBIO55434.2022.10011803","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011803","url":null,"abstract":"A climbing robot for lunar caves and craters, called a tethered-climbing robot, is proposed. It consists of a robotic platform with a robotic arm which is suspended via tethers from multiple grippers. It achieves spatial climbing locomotion by relocating the grippers with the arm and by controlling the length of the tethers. In this paper, the kinematics and statics of a tethered-climbing robot are derived, and a method to calculate the workspace of the extendable arm is introduced. Furthermore, the gait and workspace of a generic tethered-climbing robot under lunar gravity are analyzed.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125361686","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011751
Xu Shi, Wei Xu, Weichao Guo, X. Sheng
With the development of shared control technology for humanoid prosthetic hands, more and more research is focused on vision-based machine decision making. In this paper, we propose a miniaturized eye-in-hand target object prediction and action decision-making framework for the humanoid hand “approach-grasp” sequence. Our prediction system can simultaneously predict the target object and detect temporal localization of the grasp action. The system is divided into three main modules: feature logging, target filtering and grasp triggering. In this paper, the optimal configuration of the hyper-parameters designed in each module is performed experimentally. We also propose a prediction quality assessment method for “approach-grasp” behavior, including instance level, sequence level and action decision level. With the optimal hyper-parameter configuration, the predicting system perform averagely to 0.854 at instance prediction accuracy (IP), 0.643 at grasp action prediction accuracy (GP). It also has good predictive stability for most classes of objects with number of predicting changes (NPC) below 6.
{"title":"Target prediction and temporal localization of grasping action for vision-assisted prosthetic hand","authors":"Xu Shi, Wei Xu, Weichao Guo, X. Sheng","doi":"10.1109/ROBIO55434.2022.10011751","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011751","url":null,"abstract":"With the development of shared control technology for humanoid prosthetic hands, more and more research is focused on vision-based machine decision making. In this paper, we propose a miniaturized eye-in-hand target object prediction and action decision-making framework for the humanoid hand “approach-grasp” sequence. Our prediction system can simultaneously predict the target object and detect temporal localization of the grasp action. The system is divided into three main modules: feature logging, target filtering and grasp triggering. In this paper, the optimal configuration of the hyper-parameters designed in each module is performed experimentally. We also propose a prediction quality assessment method for “approach-grasp” behavior, including instance level, sequence level and action decision level. With the optimal hyper-parameter configuration, the predicting system perform averagely to 0.854 at instance prediction accuracy (IP), 0.643 at grasp action prediction accuracy (GP). It also has good predictive stability for most classes of objects with number of predicting changes (NPC) below 6.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122313511","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10012003
Sihui Liu, Pu Duan, Jianda Han, Ningbo Yu
Hand exoskeletons are attracting rising research interest for assistance in daily life. Friction is a critical issue for hand exoskeletons intended to enable dexterous finger movements. This paper presents a rigid-soft hybrid assistive hand exoskeleton using a low friction mechanism based on the multi-layered springs with rolling contact. The low friction designs not only facilitate the high transparency of the device, but also the possibility of accurate modeling in mechanics. Regarding the large deformation nature of the nonlinear mechanism, finite element analysis (FEA) has been used to explore its kinematic and kinetic characteristics. Experiments were carried out on the implemented prototype to compare the numerical results with the measured. The results demonstrate that this modeling method can provide valuable guidance for better parameter selection and optimization.
{"title":"Design and Evaluation of a Low Friction Rigid-Soft Hybrid Mechanism for Hand Exoskeletons with Finite Element Analysis","authors":"Sihui Liu, Pu Duan, Jianda Han, Ningbo Yu","doi":"10.1109/ROBIO55434.2022.10012003","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10012003","url":null,"abstract":"Hand exoskeletons are attracting rising research interest for assistance in daily life. Friction is a critical issue for hand exoskeletons intended to enable dexterous finger movements. This paper presents a rigid-soft hybrid assistive hand exoskeleton using a low friction mechanism based on the multi-layered springs with rolling contact. The low friction designs not only facilitate the high transparency of the device, but also the possibility of accurate modeling in mechanics. Regarding the large deformation nature of the nonlinear mechanism, finite element analysis (FEA) has been used to explore its kinematic and kinetic characteristics. Experiments were carried out on the implemented prototype to compare the numerical results with the measured. The results demonstrate that this modeling method can provide valuable guidance for better parameter selection and optimization.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129453224","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011909
Kexin Xiang, Weiqun Wang, Z. Hou, Chutian Zhang, Jiaxing Wang, Weiguo Shi, Yuze Jiao, Tianyu Lin
Accurate rehabilitation assessments are essential for designing effective rehabilitation methods and helping patients recover better. It's well known that commonly used scale assessment methods for neurorehabilitation suffer from the issue of subjectivity, thus investigation of objective assessment methods is very necessary. Muscle synergy analysis can be uesd to assess limb motor functions from the perspective of neuromuscular control. In this paper, a method for evaluation of human lower limb motor functions based on muscle synergy analysis is presented. Muscle synergy modules are designed using surface electromyography (sEMG) signals of the subjects' lower limbs by non-negative matrix factorizations (NMF). By comparing the cosine similarities of these synergy modules, it can be seen that muscle synergies of healthy subjects and patients are significantly different, while they are similar among healthy subjects. Therefore, a reference synergy module (RSM) is designed by averaging the muscle synergy modules for healthy subjects, and the similarities can be calculated by comparing the synergy modules for healthy subjects or patients with the RSM. In the experiment carried out in this study, average similarities of the three synergy modules for healthy subjects are respectively 0.97166, 0.87368 and 0.84932, and on the other hand, the average similarities for the three synergy modules for patients are respectively 0.59979, 0.56426 and 0.69042. Therefore, the similarities for healthy subjects are much higher than those for SCI patients, which denotes that the similarity between an individual synergy module and the RSM can be used as an objective assessing index for evaluating patients' motor function.
{"title":"Muscle Synergy Analysis Based on NMF for Lower Limb Motor Function Assessment","authors":"Kexin Xiang, Weiqun Wang, Z. Hou, Chutian Zhang, Jiaxing Wang, Weiguo Shi, Yuze Jiao, Tianyu Lin","doi":"10.1109/ROBIO55434.2022.10011909","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011909","url":null,"abstract":"Accurate rehabilitation assessments are essential for designing effective rehabilitation methods and helping patients recover better. It's well known that commonly used scale assessment methods for neurorehabilitation suffer from the issue of subjectivity, thus investigation of objective assessment methods is very necessary. Muscle synergy analysis can be uesd to assess limb motor functions from the perspective of neuromuscular control. In this paper, a method for evaluation of human lower limb motor functions based on muscle synergy analysis is presented. Muscle synergy modules are designed using surface electromyography (sEMG) signals of the subjects' lower limbs by non-negative matrix factorizations (NMF). By comparing the cosine similarities of these synergy modules, it can be seen that muscle synergies of healthy subjects and patients are significantly different, while they are similar among healthy subjects. Therefore, a reference synergy module (RSM) is designed by averaging the muscle synergy modules for healthy subjects, and the similarities can be calculated by comparing the synergy modules for healthy subjects or patients with the RSM. In the experiment carried out in this study, average similarities of the three synergy modules for healthy subjects are respectively 0.97166, 0.87368 and 0.84932, and on the other hand, the average similarities for the three synergy modules for patients are respectively 0.59979, 0.56426 and 0.69042. Therefore, the similarities for healthy subjects are much higher than those for SCI patients, which denotes that the similarity between an individual synergy module and the RSM can be used as an objective assessing index for evaluating patients' motor function.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129493327","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011641
Qiqi Li, Xiangrong Xu, Hao Yang, Xiaoyi Wang, Zhixiong Wang, Haiyan Wang, Shanshan Xu, A. Rodic, P. Petrovic
When the manipulator performs the operation task, there are modeling errors and the influence of external disturbance, which is easy to lead to the large tracking error of the manipulator end trajectory. Firstly, according to the structure of the manipulator, the dynamic model of the manipulator is established. Then RBF neural network and self -adaptation are introduced. Compared with the traditional error function, the sliding mode function is introduced in the algorithm, which can ensure the system to approach the desired trajectory quickly. The neural network used has the ability to estimate the uncertainty of the system and reduce the bad influence of interference on the system. Adaptive law and robust term are also introduced to improve the performance of the system. Finally, Lyapunov function is used to prove the stability of the system, and MATLAB/SIMULINK simulation software is used to carry out simulation experiments. Simulation results show that the algorithm has a good effect on disturbance suppression, and the end tracking accuracy is also improved.
{"title":"An Adaptive Control of Manipulator Based on RBF Neural Network Approximation","authors":"Qiqi Li, Xiangrong Xu, Hao Yang, Xiaoyi Wang, Zhixiong Wang, Haiyan Wang, Shanshan Xu, A. Rodic, P. Petrovic","doi":"10.1109/ROBIO55434.2022.10011641","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011641","url":null,"abstract":"When the manipulator performs the operation task, there are modeling errors and the influence of external disturbance, which is easy to lead to the large tracking error of the manipulator end trajectory. Firstly, according to the structure of the manipulator, the dynamic model of the manipulator is established. Then RBF neural network and self -adaptation are introduced. Compared with the traditional error function, the sliding mode function is introduced in the algorithm, which can ensure the system to approach the desired trajectory quickly. The neural network used has the ability to estimate the uncertainty of the system and reduce the bad influence of interference on the system. Adaptive law and robust term are also introduced to improve the performance of the system. Finally, Lyapunov function is used to prove the stability of the system, and MATLAB/SIMULINK simulation software is used to carry out simulation experiments. Simulation results show that the algorithm has a good effect on disturbance suppression, and the end tracking accuracy is also improved.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"316 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129947630","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011777
Valentin Ameres, Meriem Chetmi, Lucas Artmann, Tim C. Lueth
Computed Tomography (CT) and 3D reconstruction contribute significantly to reverse engineering as well as to additive manufacturing. Utilizing CT scans, surface information as well as inner details of objects of interest can be recorded non-destructively. In this work, a low-resolution computed tomography cone beam (CBCT) scanner was used to scan, reconstruct and print plastic components in order to create 3D copies. Software based calibration using an additively manufactured two layer plastic phantom containing steel ball bearings was used to detect and correct geometrical alignment errors and improve reconstruction quality. A phantom was designed to be printed additively and assembled without the help of further tools, with an axial connection to the CBCT. Corrections were applied to the two-dimensional 300x300 pixel X-ray projections before reconstruction. A reconstructed volume of 212x212x212 voxels was achieved using either the inverse-Radon-Transformation-based Feldkamp Davis Krauss (FDK) or Simultaneous Algebraic Reconstruction Technique (SART) algorithm. In an experiment, a plastic phantom was fabricated and used for misalignment correction. Two reconstructions of uncorrected and corrected projections of a 30 mm plastic cube with center bore were subsequently compared to each other in terms of density. The cube reconstructed from corrected projections had higher voxel density values and sharper slices, showing the successful fabrication and use of the plastic phantom.
计算机断层扫描(CT)和3D重建对逆向工程和增材制造做出了重大贡献。利用CT扫描，可以无损地记录感兴趣物体的表面信息和内部细节。在这项工作中，使用低分辨率计算机断层扫描锥束(CBCT)扫描仪扫描，重建和打印塑料部件，以创建3D副本。利用增材制造的含钢球轴承双层塑料模体进行软件标定，检测和修正几何对中误差，提高重建质量。设计了一个模体，无需其他工具即可打印和组装，并与CBCT进行轴向连接。重建前对二维300x300像素x射线投影进行校正。使用基于反radon变换的Feldkamp Davis Krauss (FDK)或同步代数重建技术(SART)算法实现了212x212x212体素的重建体积。在实验中，制作了一种塑料模体，并将其用于校准误差。随后，在密度方面相互比较了30 mm具有中心孔的塑料立方体的未校正和校正投影的两个重建。通过修正投影重建的立方体具有更高的体素密度值和更清晰的切片，表明塑料幻影的成功制造和使用。
{"title":"Additively Manufactured Primitive Plastic Phantom for Calibration of Low-Resolution Computed Tomography Cone Beam Scanner for Additive Creation of 3D Copies using Inverse Radon Transform","authors":"Valentin Ameres, Meriem Chetmi, Lucas Artmann, Tim C. Lueth","doi":"10.1109/ROBIO55434.2022.10011777","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011777","url":null,"abstract":"Computed Tomography (CT) and 3D reconstruction contribute significantly to reverse engineering as well as to additive manufacturing. Utilizing CT scans, surface information as well as inner details of objects of interest can be recorded non-destructively. In this work, a low-resolution computed tomography cone beam (CBCT) scanner was used to scan, reconstruct and print plastic components in order to create 3D copies. Software based calibration using an additively manufactured two layer plastic phantom containing steel ball bearings was used to detect and correct geometrical alignment errors and improve reconstruction quality. A phantom was designed to be printed additively and assembled without the help of further tools, with an axial connection to the CBCT. Corrections were applied to the two-dimensional 300x300 pixel X-ray projections before reconstruction. A reconstructed volume of 212x212x212 voxels was achieved using either the inverse-Radon-Transformation-based Feldkamp Davis Krauss (FDK) or Simultaneous Algebraic Reconstruction Technique (SART) algorithm. In an experiment, a plastic phantom was fabricated and used for misalignment correction. Two reconstructions of uncorrected and corrected projections of a 30 mm plastic cube with center bore were subsequently compared to each other in terms of density. The cube reconstructed from corrected projections had higher voxel density values and sharper slices, showing the successful fabrication and use of the plastic phantom.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130600310","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011923
Jinzhou Wang, Ran Huang
The ability of mobile robots to navigate in an unfamiliar environment in human terms is decisive for their applicability to practical activities. Bearing this view in mind, we propose a novel framework for navigation in settings where the environment is a priori unknown and can only be partially observed by the robot with onboard sensors. The proposed hierarchical navigation solution combines deep reinforcement learning-based perception with model-based control. Specifically, a deep reinforcement learning (DRL) network based on Soft Actor-Critic (SAC) algorithm and Long Short-Term Memory (LSTM) is trained to map the robot's states, 2D lidar inputs and goal position to a series of local waypoints which are optimal in the sense of collision avoidance. The waypoints are then employed by a dynamic window approach (DWA) based planner to generate a smooth and dynamically feasible trajectory that is tracked by using feedback control. The experiments performed on an actual wheeled robot demonstrate that the proposed scheme enables the robot to reach goal locations more reliably and efficiently in unstructured environments in comparison with purely learning based approach.
{"title":"A Mapless Navigation Method Based on Deep Reinforcement Learning and Path Planning","authors":"Jinzhou Wang, Ran Huang","doi":"10.1109/ROBIO55434.2022.10011923","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011923","url":null,"abstract":"The ability of mobile robots to navigate in an unfamiliar environment in human terms is decisive for their applicability to practical activities. Bearing this view in mind, we propose a novel framework for navigation in settings where the environment is a priori unknown and can only be partially observed by the robot with onboard sensors. The proposed hierarchical navigation solution combines deep reinforcement learning-based perception with model-based control. Specifically, a deep reinforcement learning (DRL) network based on Soft Actor-Critic (SAC) algorithm and Long Short-Term Memory (LSTM) is trained to map the robot's states, 2D lidar inputs and goal position to a series of local waypoints which are optimal in the sense of collision avoidance. The waypoints are then employed by a dynamic window approach (DWA) based planner to generate a smooth and dynamically feasible trajectory that is tracked by using feedback control. The experiments performed on an actual wheeled robot demonstrate that the proposed scheme enables the robot to reach goal locations more reliably and efficiently in unstructured environments in comparison with purely learning based approach.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129806035","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：