Pub Date : 2004-12-01DOI: 10.1109/RAMECH.2004.1438902
Jian Shen, J. Guzman, T. Ng, B. S. Chew
Tele-operated systems allow humans to extend their physical capabilities and enable them to intervene in hazardous operations or where their presence is not possible. However, the operation of such systems over long periods has proved to be difficult and stressful. Consequently, means to facilitate their use are the subject of much study and experimental work. In this paper, we propose a collaborative-shared control strategy that combines the operator abilities with robotic-based tasks to render these systems more flexible and robust. In our method, the collaborative control component is responsible for allowing operator intervention when the robot is facing complex situations, whilst the shared control component provides an automatic control mechanism to assist and to monitor-correct irrational operator actions. The paper demonstrates how collaborative and shared control strategies work together to facilitate the teleoperated control of a mobile platform in a cluttered environment. The experimental results include applications to surveillance and to search & rescue operations. In addition, a key component in the form of a hybrid obstacle avoidance module is introduced that allows the robot to be guided on a task basis by the operator at a distance.
{"title":"A collaborative-shared control system with safe obstacle avoidance capability","authors":"Jian Shen, J. Guzman, T. Ng, B. S. Chew","doi":"10.1109/RAMECH.2004.1438902","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438902","url":null,"abstract":"Tele-operated systems allow humans to extend their physical capabilities and enable them to intervene in hazardous operations or where their presence is not possible. However, the operation of such systems over long periods has proved to be difficult and stressful. Consequently, means to facilitate their use are the subject of much study and experimental work. In this paper, we propose a collaborative-shared control strategy that combines the operator abilities with robotic-based tasks to render these systems more flexible and robust. In our method, the collaborative control component is responsible for allowing operator intervention when the robot is facing complex situations, whilst the shared control component provides an automatic control mechanism to assist and to monitor-correct irrational operator actions. The paper demonstrates how collaborative and shared control strategies work together to facilitate the teleoperated control of a mobile platform in a cluttered environment. The experimental results include applications to surveillance and to search & rescue operations. In addition, a key component in the form of a hybrid obstacle avoidance module is introduced that allows the robot to be guided on a task basis by the operator at a distance.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122343245","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1438002
Edward Wong, R. Jarvis
This paper describes a stereo vision guided humanoid that can perform real time obstacle detection, path analysis and navigation planning on a carpet floor. The real time obstacle detection algorithm uses the two dimensional disparity gradients approach to detect the obstacle on the floor without constructing the floor plane and affine adjustment even though the baseline of the camera system is not parallel with the floor. The size of the obstacle that can be detected is as small as 30 mm in diameter. The navigation planning is performed by using a distance transform method in which a shortest path is found and then the number of footsteps required to reach the destination is calculated.
{"title":"Real time obstacle detection and navigation planning for a humanoid robot in an indoor environment","authors":"Edward Wong, R. Jarvis","doi":"10.1109/RAMECH.2004.1438002","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438002","url":null,"abstract":"This paper describes a stereo vision guided humanoid that can perform real time obstacle detection, path analysis and navigation planning on a carpet floor. The real time obstacle detection algorithm uses the two dimensional disparity gradients approach to detect the obstacle on the floor without constructing the floor plane and affine adjustment even though the baseline of the camera system is not parallel with the floor. The size of the obstacle that can be detected is as small as 30 mm in diameter. The navigation planning is performed by using a distance transform method in which a shortest path is found and then the number of footsteps required to reach the destination is calculated.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114172164","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1438051
Jae Byung Park, Youngrock Yoon
This paper presents a robust histogram based tracking algorithm that is capable of detecting specular highlights on objects or faces to be tracked. The materials with shiny and smooth surfaces such as car exterior, ceramics or glasses often exhibit specularities which are highly saturated regions in the image that are produced by mirrorlike reflections. Whenever confronted with such specular highlights on the target objects, the results of segmentation and tracking become inaccurate and unreliable. Speaking of real-time color object tracking, there are two major issues that are associated with such specular highlights. First issue is how to detect specular highlights suddenly appearing in the image sequence. Second one is how the detected specular highlights can be correspondingly considered to improve the tracking performance. In this paper, we describe our specularity detection method that can he applied to every pair of consecutive frames in the tracking sequence. Experimental results of two tracking systems: (1) with specularity detection and (2) without handling specularities are compared to show the improvement. This method has been successfully tested on multiple tracking tasks with monochromatic objects.
{"title":"Tracking objects and faces using color histograms enhanced with specularity detection","authors":"Jae Byung Park, Youngrock Yoon","doi":"10.1109/RAMECH.2004.1438051","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438051","url":null,"abstract":"This paper presents a robust histogram based tracking algorithm that is capable of detecting specular highlights on objects or faces to be tracked. The materials with shiny and smooth surfaces such as car exterior, ceramics or glasses often exhibit specularities which are highly saturated regions in the image that are produced by mirrorlike reflections. Whenever confronted with such specular highlights on the target objects, the results of segmentation and tracking become inaccurate and unreliable. Speaking of real-time color object tracking, there are two major issues that are associated with such specular highlights. First issue is how to detect specular highlights suddenly appearing in the image sequence. Second one is how the detected specular highlights can be correspondingly considered to improve the tracking performance. In this paper, we describe our specularity detection method that can he applied to every pair of consecutive frames in the tracking sequence. Experimental results of two tracking systems: (1) with specularity detection and (2) without handling specularities are compared to show the improvement. This method has been successfully tested on multiple tracking tasks with monochromatic objects.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121251498","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1438915
Jianfa Wang, Wensheng Yin, Y. Zhu, G. Duan
Identification and control of an air bearing linear stage driven by a voice coil motor are considered. The load of the stage is more than 5 kg, and the model has to include the mode of mechanism for high bandwidth and high precision motion control. Identification based on normalized coprime factors is introduced for this purpose. A precise model with high order can be derived from the identification, but the order of the model is too high to control design, therefore, model reduction is performed. Finally, a polynomial pole-placement combined with sensitivity function shaping is carried out. The experimental result shows the stage can achieve 10 nm position step easily.
{"title":"Identification and super-precision control of a linear stage driven by a voice coil motor","authors":"Jianfa Wang, Wensheng Yin, Y. Zhu, G. Duan","doi":"10.1109/RAMECH.2004.1438915","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438915","url":null,"abstract":"Identification and control of an air bearing linear stage driven by a voice coil motor are considered. The load of the stage is more than 5 kg, and the model has to include the mode of mechanism for high bandwidth and high precision motion control. Identification based on normalized coprime factors is introduced for this purpose. A precise model with high order can be derived from the identification, but the order of the model is too high to control design, therefore, model reduction is performed. Finally, a polynomial pole-placement combined with sensitivity function shaping is carried out. The experimental result shows the stage can achieve 10 nm position step easily.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123790808","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1438942
Changjiu Zhou, Pik Kong Yue, Jun Ni, Shan-Ben Chan
In this paper, we formulate gait synthesis of humanoid biped locomotion as an optimization problem with consideration of some constraints, e.g. zero-moment point (ZMP) constraints for dynamically stable locomotion, internal forces constraints for smooth transition, geometric constraints for walking on an uneven floor, e.g. sloping surface and etc. In the frame of gait synthesis tied with constraint functions, computational learning methods can be incorporated to further improve the gait. The effectiveness of the proposed dynamically stable gait planning and learning approach for humanoid walking on both even floor and sloping surface has been successfully tested on our humanoid soccer robots named Robo-Erectus, which won first place in the RoboCup 2003 Humanoid League Free Performance competition and got 4 silver awards in the RoboCup Humanoid League 2004.
{"title":"Dynamically stable gait planning for a humanoid robot to climb sloping surface","authors":"Changjiu Zhou, Pik Kong Yue, Jun Ni, Shan-Ben Chan","doi":"10.1109/RAMECH.2004.1438942","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438942","url":null,"abstract":"In this paper, we formulate gait synthesis of humanoid biped locomotion as an optimization problem with consideration of some constraints, e.g. zero-moment point (ZMP) constraints for dynamically stable locomotion, internal forces constraints for smooth transition, geometric constraints for walking on an uneven floor, e.g. sloping surface and etc. In the frame of gait synthesis tied with constraint functions, computational learning methods can be incorporated to further improve the gait. The effectiveness of the proposed dynamically stable gait planning and learning approach for humanoid walking on both even floor and sloping surface has been successfully tested on our humanoid soccer robots named Robo-Erectus, which won first place in the RoboCup 2003 Humanoid League Free Performance competition and got 4 silver awards in the RoboCup Humanoid League 2004.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125293222","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1438010
M. Monnin, Daniel Racoceanu, N. Zerhouni
This paper studies diagnosis-aid systems that use artificial intelligence tools. This kind of system is very interesting in an uncertain industrial environment, especially flexible production systems. An overview of the most important artificial intelligence diagnosis tools is given. For each tool, we focus on diagnosis principles and its advantages and disadvantages. That allows us to extract four important points that a diagnosis tool should fulfil. Using these results, we propose a tool based on fuzzy Petri nets which allows to make a diagnosis using a model that is easy to build and that takes into account the uncertainties of maintenance knowledge. This tool provides abductive approaches of a fault propagation system with efficient localization and characterization of the fault origin. We apply our tool to an illustrative example of flexible system diagnosis.
{"title":"Overview on diagnosis methods using artificial intelligence application of fuzzy Petri nets","authors":"M. Monnin, Daniel Racoceanu, N. Zerhouni","doi":"10.1109/RAMECH.2004.1438010","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438010","url":null,"abstract":"This paper studies diagnosis-aid systems that use artificial intelligence tools. This kind of system is very interesting in an uncertain industrial environment, especially flexible production systems. An overview of the most important artificial intelligence diagnosis tools is given. For each tool, we focus on diagnosis principles and its advantages and disadvantages. That allows us to extract four important points that a diagnosis tool should fulfil. Using these results, we propose a tool based on fuzzy Petri nets which allows to make a diagnosis using a model that is easy to build and that takes into account the uncertainties of maintenance knowledge. This tool provides abductive approaches of a fault propagation system with efficient localization and characterization of the fault origin. We apply our tool to an illustrative example of flexible system diagnosis.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127732439","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1437989
M. Younis, Georg Frey
The complexity of existing PLC programs precludes dealing with or modifying them. The interest in the formalization of PLC programs has increased in recent years to overcome this problem. Formal methods can provide for the development of PLC programs, since they serve as a medium to analyze and verify them due to increased awareness of safety and quality. This is done by performing what is known as verification and validation (V&V). Moreover formal methods support reuse of already implemented PLC programs to meet new production demands. This paper examines different possibilities to formalize PLC programs. It explains the pros and cons of these different alternatives. The paper outlines a formal description of timers and counters used in PLC programs according to the alternative that fulfills the criteria best.
{"title":"Formalization of PLC programs to sustain reliability","authors":"M. Younis, Georg Frey","doi":"10.1109/RAMECH.2004.1437989","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1437989","url":null,"abstract":"The complexity of existing PLC programs precludes dealing with or modifying them. The interest in the formalization of PLC programs has increased in recent years to overcome this problem. Formal methods can provide for the development of PLC programs, since they serve as a medium to analyze and verify them due to increased awareness of safety and quality. This is done by performing what is known as verification and validation (V&V). Moreover formal methods support reuse of already implemented PLC programs to meet new production demands. This paper examines different possibilities to formalize PLC programs. It explains the pros and cons of these different alternatives. The paper outlines a formal description of timers and counters used in PLC programs according to the alternative that fulfills the criteria best.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133270848","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1438941
Zhe Tang, Changjiu Zhou, Zeng-qi Sun
Penalty kicking is a specific task for humanoid robots, which is defined by the robotic soccer community. An effective and powerful kicking is a challenging task because of balance. During the period of kicking, the kicking leg moves very quickly and therefore the dynamics should not be ignored. Furthermore, during the kicking, the center of gravity of the robot moves to the front. These two factors greatly influence the balance of the humanoid robot. In this paper, we keep the robot balanced through adjusting the stance leg's ankle joint, both the dynamics and CG changes are considered. The performance and applicability of the proposed method are illustrated both through simulation and real-time control of a humanoid robot developed by the Humanoid Group (www.robo-erectus.org) at Singapore Polytechnic.
点球是人形机器人的一项特殊任务，由机器人足球界定义。由于平衡的关系，有效而有力的踢腿是一项具有挑战性的任务。在踢腿的过程中，踢腿的动作非常快，因此不应该忽视动力学。此外，在踢腿过程中，机器人的重心向前方移动。这两个因素对仿人机器人的平衡有很大的影响。在本文中，我们通过调整站立腿的踝关节来保持机器人的平衡，同时考虑了动力学和CG的变化。通过新加坡理工学院humanoid Group (www.robo-erectus.org)开发的仿人机器人的仿真和实时控制，说明了所提出方法的性能和适用性。
{"title":"Balance of penalty kicking for a biped robot","authors":"Zhe Tang, Changjiu Zhou, Zeng-qi Sun","doi":"10.1109/RAMECH.2004.1438941","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438941","url":null,"abstract":"Penalty kicking is a specific task for humanoid robots, which is defined by the robotic soccer community. An effective and powerful kicking is a challenging task because of balance. During the period of kicking, the kicking leg moves very quickly and therefore the dynamics should not be ignored. Furthermore, during the kicking, the center of gravity of the robot moves to the front. These two factors greatly influence the balance of the humanoid robot. In this paper, we keep the robot balanced through adjusting the stance leg's ankle joint, both the dynamics and CG changes are considered. The performance and applicability of the proposed method are illustrated both through simulation and real-time control of a humanoid robot developed by the Humanoid Group (www.robo-erectus.org) at Singapore Polytechnic.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114034478","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1438951
Yanjie Liu, Lining Sun, Qingxin Meng
This paper presents a new 2-DOF planar parallel robot with high speed and high precision. Harmonic drive is adopted between an AC servomotor and its driven link in each drive joint, and at the same time a rotary encoder feeds the driven link angle into the position controller of each drive joint. Thus, the resolution of the drive joint is improved greatly. However, flexibility of harmonic drive during high-speed motion causes the sharp elastic vibration. Therefore, an acceleration feedback controller is especially designed to increase the damping coefficient and restrain the elastic vibration. Furthermore, the stability of the entire system including the drive joint's position controller and the acceleration feedback controller is proved using a Lyapunov approach. The experiments of trajectory tracking are conducted on the robotic system, and the results validate the proposed control algorithm, contrasted with that obtained by classical PD control without the acceleration feedback loop.
{"title":"Acceleration feedback control of a harmonic drive parallel robot","authors":"Yanjie Liu, Lining Sun, Qingxin Meng","doi":"10.1109/RAMECH.2004.1438951","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1438951","url":null,"abstract":"This paper presents a new 2-DOF planar parallel robot with high speed and high precision. Harmonic drive is adopted between an AC servomotor and its driven link in each drive joint, and at the same time a rotary encoder feeds the driven link angle into the position controller of each drive joint. Thus, the resolution of the drive joint is improved greatly. However, flexibility of harmonic drive during high-speed motion causes the sharp elastic vibration. Therefore, an acceleration feedback controller is especially designed to increase the damping coefficient and restrain the elastic vibration. Furthermore, the stability of the entire system including the drive joint's position controller and the acceleration feedback controller is proved using a Lyapunov approach. The experiments of trajectory tracking are conducted on the robotic system, and the results validate the proposed control algorithm, contrasted with that obtained by classical PD control without the acceleration feedback loop.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114361805","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 : 2004-12-01DOI: 10.1109/RAMECH.2004.1437996
S. Ge, C. Fua, Wei-Ming Liew
This paper presents a method for synthesizing classes of potential functions, which corresponds to commonly used formations, from a general formation potential function by altering the values of a fixed set of parameters. These potential functions may then be used for formation control in swarms of agents. The properties of the potential functions are also examined in this paper. In addition, obstacle avoidance and target tracking behaviors are also implemented on the individual agents. Simulation studies have been carried out to verify the effectiveness of our approach.
{"title":"Swarm formations using the general formation potential function","authors":"S. Ge, C. Fua, Wei-Ming Liew","doi":"10.1109/RAMECH.2004.1437996","DOIUrl":"https://doi.org/10.1109/RAMECH.2004.1437996","url":null,"abstract":"This paper presents a method for synthesizing classes of potential functions, which corresponds to commonly used formations, from a general formation potential function by altering the values of a fixed set of parameters. These potential functions may then be used for formation control in swarms of agents. The properties of the potential functions are also examined in this paper. In addition, obstacle avoidance and target tracking behaviors are also implemented on the individual agents. Simulation studies have been carried out to verify the effectiveness of our approach.","PeriodicalId":252964,"journal":{"name":"IEEE Conference on Robotics, Automation and Mechatronics, 2004.","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114468827","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：