Pub Date : 2015-07-27DOI: 10.1109/ICAR.2015.7251504
B. Çalli, Arjun Singh, Aaron Walsman, S. Srinivasa, P. Abbeel, A. Dollar
In this paper we present the Yale-CMU-Berkeley (YCB) Object and Model set, intended to be used for benchmarking in robotic grasping and manipulation research. The objects in the set are designed to cover various aspects of the manipulation problem; it includes objects of daily life with different shapes, sizes, textures, weight and rigidity, as well as some widely used manipulation tests. The associated database provides high-resolution RGBD scans, physical properties and geometric models of the objects for easy incorporation into manipulation and planning software platforms. A comprehensive literature survey on existing benchmarks and object datasets is also presented and their scope and limitations are discussed. The set will be freely distributed to research groups worldwide at a series of tutorials at robotics conferences, and will be otherwise available at a reasonable purchase cost.
{"title":"The YCB object and Model set: Towards common benchmarks for manipulation research","authors":"B. Çalli, Arjun Singh, Aaron Walsman, S. Srinivasa, P. Abbeel, A. Dollar","doi":"10.1109/ICAR.2015.7251504","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251504","url":null,"abstract":"In this paper we present the Yale-CMU-Berkeley (YCB) Object and Model set, intended to be used for benchmarking in robotic grasping and manipulation research. The objects in the set are designed to cover various aspects of the manipulation problem; it includes objects of daily life with different shapes, sizes, textures, weight and rigidity, as well as some widely used manipulation tests. The associated database provides high-resolution RGBD scans, physical properties and geometric models of the objects for easy incorporation into manipulation and planning software platforms. A comprehensive literature survey on existing benchmarks and object datasets is also presented and their scope and limitations are discussed. The set will be freely distributed to research groups worldwide at a series of tutorials at robotics conferences, and will be otherwise available at a reasonable purchase cost.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130872338","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251513
M. Falahi, Sima Sobhiyeh, A. Rezaie, S. Motamedi
In this research a new robot learning method based on imitation is introduced which enables a robot to learn new trajectories by only one demonstration. This one-shot learning approach is based on Orthogonal basis Functions and Template Matching (OFTM) which was previously introduced by our group and implemented using the Fourier basis functions. In this paper the W-OFTM method is presented which employs the wavelet transform in the OFTM approach. In W-OFTM the wavelet orthogonal basis functions are included in the dictionary of primitive motions, alongside a few well-established templates. One of the major advantages of this approach is enabling the robot to reproduce all trajectories in its workspace. In this research, a thresholding parameter was automatically set in the F-OFTM and W-OFTM methods in order to filter out unimportant coefficients and reduce the occupied memory space while holding the increased error below a certain acceptable value. In the experimental trial, the proposed method was applied to a chef robot in order to learn the task of stirring food. Results indicate that in comparison to the GMM-GMR method, the W-OFTM method provides more accurate results with much less delay. Furthermore, the advantage of the proposed method over the state of the art method increases as the numbers of samples contained in a trajectory increases.
{"title":"Wavelet based OFTM for learning stirring food by imitation","authors":"M. Falahi, Sima Sobhiyeh, A. Rezaie, S. Motamedi","doi":"10.1109/ICAR.2015.7251513","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251513","url":null,"abstract":"In this research a new robot learning method based on imitation is introduced which enables a robot to learn new trajectories by only one demonstration. This one-shot learning approach is based on Orthogonal basis Functions and Template Matching (OFTM) which was previously introduced by our group and implemented using the Fourier basis functions. In this paper the W-OFTM method is presented which employs the wavelet transform in the OFTM approach. In W-OFTM the wavelet orthogonal basis functions are included in the dictionary of primitive motions, alongside a few well-established templates. One of the major advantages of this approach is enabling the robot to reproduce all trajectories in its workspace. In this research, a thresholding parameter was automatically set in the F-OFTM and W-OFTM methods in order to filter out unimportant coefficients and reduce the occupied memory space while holding the increased error below a certain acceptable value. In the experimental trial, the proposed method was applied to a chef robot in order to learn the task of stirring food. Results indicate that in comparison to the GMM-GMR method, the W-OFTM method provides more accurate results with much less delay. Furthermore, the advantage of the proposed method over the state of the art method increases as the numbers of samples contained in a trajectory increases.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131021623","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251482
M. Ragaglia, L. Bascetta, P. Rocco
In order to enable safe and efficient human-robot interaction it is beneficial for the robot control system to be able not only to detect the presence and track the motion of human workers entering the robotic cell, but also to predict in the least possible time their trajectory and the area they are heading to. This paper proposes an innovative particle filtering strategy addressing at the same time the problems of Human Detection and Tracking and Intention Estimation, based on low-cost commercial RGB surveillance cameras, a map of the robotic cell environment, and a probabilistic description of the trajectories followed by human workers inside the cell. Results of several validation experiments are presented.
{"title":"Detecting, tracking and predicting human motion inside an industrial robotic cell using a map-based particle filtering strategy","authors":"M. Ragaglia, L. Bascetta, P. Rocco","doi":"10.1109/ICAR.2015.7251482","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251482","url":null,"abstract":"In order to enable safe and efficient human-robot interaction it is beneficial for the robot control system to be able not only to detect the presence and track the motion of human workers entering the robotic cell, but also to predict in the least possible time their trajectory and the area they are heading to. This paper proposes an innovative particle filtering strategy addressing at the same time the problems of Human Detection and Tracking and Intention Estimation, based on low-cost commercial RGB surveillance cameras, a map of the robotic cell environment, and a probabilistic description of the trajectories followed by human workers inside the cell. Results of several validation experiments are presented.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121581666","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251494
Hyunmin Do, Byung-In Kim, Chanhun Park, J. Kyung
Parallel robot has been usually used for pick-and place motion in very high speed environment to enhance the productivity. The high speed parallel robot is proposed for handling the solar cell in this paper. However the target processes are not just limited to the solar cell. The control algorithm is developed to achieve the high speed tracking control of pick-and-place motion. Also the prototype machine is designed and the cycle time and the repeatability of the proposed robot are validated. The method using the feedback and feedforward control is applied to the developed parallel robot and the performance is proven through the experiments. To improve the performance, the error for tracking and synchronization are simultaneously considered.
{"title":"Tracking control of 3 DOF parallel robots: Prototype design and experiments","authors":"Hyunmin Do, Byung-In Kim, Chanhun Park, J. Kyung","doi":"10.1109/ICAR.2015.7251494","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251494","url":null,"abstract":"Parallel robot has been usually used for pick-and place motion in very high speed environment to enhance the productivity. The high speed parallel robot is proposed for handling the solar cell in this paper. However the target processes are not just limited to the solar cell. The control algorithm is developed to achieve the high speed tracking control of pick-and-place motion. Also the prototype machine is designed and the cycle time and the repeatability of the proposed robot are validated. The method using the feedback and feedforward control is applied to the developed parallel robot and the performance is proven through the experiments. To improve the performance, the error for tracking and synchronization are simultaneously considered.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"44 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120817979","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251464
Denis Forte, B. Nemec, A. Ude
Imitation learning has been proposed as the basis for fast and efficient acquisition of new sensorimotor behaviors. Movement representations such as dynamic movement primitives were designed to enable the reproduction of the demonstrated behaviors and their modulation with respect to unexpected external perturbations. Various statistical methods were developed to generalize the acquired sensorimotor knowledge to new configurations of the robot's workspace. However, statistical methods can only be successful if enough training data are available. If this is not the case, usually the teacher must provide additional demonstrations to augment the database, thereby improving the performance of generalization. In this paper we propose an approach that enables robots to expand their knowledge database autonomously. Efficient exploration becomes possible by exploiting the structure of the search space defined by the previously acquired example movements. We show in real-world experiments that this way the robot can expand its database and improve the performance of generalization without the help of the teacher.
{"title":"Exploration in structured space of robot movements for autonomous augmentation of action knowledge","authors":"Denis Forte, B. Nemec, A. Ude","doi":"10.1109/ICAR.2015.7251464","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251464","url":null,"abstract":"Imitation learning has been proposed as the basis for fast and efficient acquisition of new sensorimotor behaviors. Movement representations such as dynamic movement primitives were designed to enable the reproduction of the demonstrated behaviors and their modulation with respect to unexpected external perturbations. Various statistical methods were developed to generalize the acquired sensorimotor knowledge to new configurations of the robot's workspace. However, statistical methods can only be successful if enough training data are available. If this is not the case, usually the teacher must provide additional demonstrations to augment the database, thereby improving the performance of generalization. In this paper we propose an approach that enables robots to expand their knowledge database autonomously. Efficient exploration becomes possible by exploiting the structure of the search space defined by the previously acquired example movements. We show in real-world experiments that this way the robot can expand its database and improve the performance of generalization without the help of the teacher.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115055578","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251498
Alessia Vignolo, S. Briot, P. Martinet, Chao Chen
Past research works have shown that it was possible to evaluate the end-effector pose of parallel robots by vision. First of all, it was proposed to directly observed the end-effector. However, this observation may be not possible (e.g. in the case of a haptic device for which the end-effector may be hidden by the user hand). Therefore, it has been proposed another type of end-effector pose estimation based on the observation of the directions of the legs. Even interesting results were obtained, this method is not suitable for some particular parallel robot families (e.g. the Monash Epicyclic-Parallel Manipulator, MEPaM). This paper proposes a new approach for the estimation of the end-effector pose: by observing the mechanism legs, it is possible to extract the Plücker coordinates of their lines and determine the end-effector pose. The new end-effector pose estimation method is applied to the MEPaM. All results are validated on a MEPaM simulator created using ADAMS/Controls and interfaced with Matlab/Simulink.
{"title":"End-effector pose estimation of the Monash Epicyclic-Parallel Manipulator through the visual observation of its legs","authors":"Alessia Vignolo, S. Briot, P. Martinet, Chao Chen","doi":"10.1109/ICAR.2015.7251498","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251498","url":null,"abstract":"Past research works have shown that it was possible to evaluate the end-effector pose of parallel robots by vision. First of all, it was proposed to directly observed the end-effector. However, this observation may be not possible (e.g. in the case of a haptic device for which the end-effector may be hidden by the user hand). Therefore, it has been proposed another type of end-effector pose estimation based on the observation of the directions of the legs. Even interesting results were obtained, this method is not suitable for some particular parallel robot families (e.g. the Monash Epicyclic-Parallel Manipulator, MEPaM). This paper proposes a new approach for the estimation of the end-effector pose: by observing the mechanism legs, it is possible to extract the Plücker coordinates of their lines and determine the end-effector pose. The new end-effector pose estimation method is applied to the MEPaM. All results are validated on a MEPaM simulator created using ADAMS/Controls and interfaced with Matlab/Simulink.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123523536","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251516
Wesam M. Jasim, Dongbing Gu
An integral backstepping control algorithm is presented for the path tracking problem of a quadrotor in this work. The dynamical model of a quadrotor is represented based on unit quaternion representation and includes some modelled aerodynamical effects as a nonlinear part. The integral backstepping controller is designed for translational part to track the desired trajectory. Stability analysis is achieved via a suitable Lyapunov function. The external disturbance and model parameters uncertainty are considered in the simulation tests to justify the proposed controller stability. Simulation results are compared with a standard backstepping controller results.
{"title":"Integral backstepping controller for quadrotor path tracking","authors":"Wesam M. Jasim, Dongbing Gu","doi":"10.1109/ICAR.2015.7251516","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251516","url":null,"abstract":"An integral backstepping control algorithm is presented for the path tracking problem of a quadrotor in this work. The dynamical model of a quadrotor is represented based on unit quaternion representation and includes some modelled aerodynamical effects as a nonlinear part. The integral backstepping controller is designed for translational part to track the desired trajectory. Stability analysis is achieved via a suitable Lyapunov function. The external disturbance and model parameters uncertainty are considered in the simulation tests to justify the proposed controller stability. Simulation results are compared with a standard backstepping controller results.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126301628","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251506
E. Cataldi, G. Antonelli
In this paper an underwater vehicle-manipulator system is considered in order to accomplish two operations, namely to turn a valve and to push a button. Realistic assumptions, such as imperfect knowledge of the environment, have been considered with the purpose to design the proper interaction control scheme. In addition, due to the poor knowledge of the underwater dynamics, model-based approaches have been avoided. The UVMS is characterized by 13 Degrees-Of-Freedoms (DOFs) and a proper task-priority, inverse kinematics controller has been designed to take into account all the DOFs, however, this paper focuses on the interaction part. The redundancy exploitation is an ongoing activity being the interaction approach fully decoupled, and thus compatible, with the redundancy resolution scheme. The validation has been achieved resorting to a realistic mathematical model, including the main dynamic effects.
{"title":"Basic interaction operations for an underwater vehicle-manipulator system","authors":"E. Cataldi, G. Antonelli","doi":"10.1109/ICAR.2015.7251506","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251506","url":null,"abstract":"In this paper an underwater vehicle-manipulator system is considered in order to accomplish two operations, namely to turn a valve and to push a button. Realistic assumptions, such as imperfect knowledge of the environment, have been considered with the purpose to design the proper interaction control scheme. In addition, due to the poor knowledge of the underwater dynamics, model-based approaches have been avoided. The UVMS is characterized by 13 Degrees-Of-Freedoms (DOFs) and a proper task-priority, inverse kinematics controller has been designed to take into account all the DOFs, however, this paper focuses on the interaction part. The redundancy exploitation is an ongoing activity being the interaction approach fully decoupled, and thus compatible, with the redundancy resolution scheme. The validation has been achieved resorting to a realistic mathematical model, including the main dynamic effects.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132573424","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7298210
Abdallah Dib, F. Charpillet
The aim of our work is to estimate the camera motion from RGB-D images in a dynamic scene. Most of the existing methods have a poor localization performance in such environments, which makes them inapplicable in real world conditions. In this paper, we propose a new dense visual odometry method that uses RANSAC to cope with dynamic scenes. We show the efficiency and robustness of the proposed method on a large set of experiments in challenging situations and from publicly available benchmark dataset. Additionally, we compare our approach to another state-of-art method based on M-estimator that is used to deal with dynamic scenes. Our method gives similar results on benchmark sequences and better results on our own dataset.
{"title":"Robust dense visual odometry for RGB-D cameras in a dynamic environment","authors":"Abdallah Dib, F. Charpillet","doi":"10.1109/ICAR.2015.7298210","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7298210","url":null,"abstract":"The aim of our work is to estimate the camera motion from RGB-D images in a dynamic scene. Most of the existing methods have a poor localization performance in such environments, which makes them inapplicable in real world conditions. In this paper, we propose a new dense visual odometry method that uses RANSAC to cope with dynamic scenes. We show the efficiency and robustness of the proposed method on a large set of experiments in challenging situations and from publicly available benchmark dataset. Additionally, we compare our approach to another state-of-art method based on M-estimator that is used to deal with dynamic scenes. Our method gives similar results on benchmark sequences and better results on our own dataset.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131106206","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 : 2015-07-27DOI: 10.1109/ICAR.2015.7251425
Sangrok Jin, Jihoon Kim, Jongwon Kim, Jangho Bae, J. Bak, Jongwon Kim, Taewon Seo
A hovering control design based on back-stepping method is proposed for a dynamic model of an underwater robot with tilting thrusters. In order to achieve various underwater tasks, a robotic platform must be able to maintain its position and orientation against ocean currents and reaction forces from the manipulator's operation. The underwater robot which has four tilting thrusters can carry out six degrees-of-freedom (DOF) motion. A dynamic model is derived for the underwater robot based on hydrodynamic analysis and nonlinear thrust vector mapping. A hovering controller based on a dynamic model is derived by using a back-stepping control method, and disturbance models, such as ocean currents and reaction from the attached manipulator, are designed. Simulations show reasonable results of the control system under disturbance.
{"title":"Back-stepping control design for an underwater robot with tilting thrusters","authors":"Sangrok Jin, Jihoon Kim, Jongwon Kim, Jangho Bae, J. Bak, Jongwon Kim, Taewon Seo","doi":"10.1109/ICAR.2015.7251425","DOIUrl":"https://doi.org/10.1109/ICAR.2015.7251425","url":null,"abstract":"A hovering control design based on back-stepping method is proposed for a dynamic model of an underwater robot with tilting thrusters. In order to achieve various underwater tasks, a robotic platform must be able to maintain its position and orientation against ocean currents and reaction forces from the manipulator's operation. The underwater robot which has four tilting thrusters can carry out six degrees-of-freedom (DOF) motion. A dynamic model is derived for the underwater robot based on hydrodynamic analysis and nonlinear thrust vector mapping. A hovering controller based on a dynamic model is derived by using a back-stepping control method, and disturbance models, such as ocean currents and reaction from the attached manipulator, are designed. Simulations show reasonable results of the control system under disturbance.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123920064","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：