Pub Date : 2012-12-01DOI: 10.1109/ICARCV.2012.6485203
Fan Wu, Xiao-dong Li
Almost all existing Iterative Learning Control (ILC) methods are specifically designed for the one-dimensional dynamical systems. And many two-dimensional dynamical systems are often required to do repeatable works in engineering fields. This paper presents a novel P-type ILC rule for the two-dimensional systems represented by Roessor's model. The proof on convergence of the proposed ILC rule is based on the solution formula of the two-dimensional Roessor's model in ILC process. By transferring the ILC tracking errors into a one-dimensional system in iteration direction, the convergence condition of the proposed ILC rule is derived.
{"title":"Iterative Learning Control for 2-D linear discrete systems with Roessor's model","authors":"Fan Wu, Xiao-dong Li","doi":"10.1109/ICARCV.2012.6485203","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485203","url":null,"abstract":"Almost all existing Iterative Learning Control (ILC) methods are specifically designed for the one-dimensional dynamical systems. And many two-dimensional dynamical systems are often required to do repeatable works in engineering fields. This paper presents a novel P-type ILC rule for the two-dimensional systems represented by Roessor's model. The proof on convergence of the proposed ILC rule is based on the solution formula of the two-dimensional Roessor's model in ILC process. By transferring the ILC tracking errors into a one-dimensional system in iteration direction, the convergence condition of the proposed ILC rule is derived.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129905857","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485378
Jian Li, Hui Li, X. Zhang, Guo-xin Pan, Q. Xiao
In order to solve the clinical application problems of existing rehabilitation robots, this paper made a local and global analysis and put forward a new design for the lower limb rehabilitation robot based on the technology of Body Weight Support Treadmill Training(BWSTT). Contrast to others, the robot has features of flexible structure, simple operation, strong practicality and low price. Methods of modular design and intensive design which usually used in Industrial Design were used in this paper, they can solve many clinical difficulties. Through preliminary clinical experiments, the design can solve and improve some problems, but it also need in-depth study and analyze.
{"title":"The design and implementation of lower limb rehabilitation robot based on BWSTT","authors":"Jian Li, Hui Li, X. Zhang, Guo-xin Pan, Q. Xiao","doi":"10.1109/ICARCV.2012.6485378","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485378","url":null,"abstract":"In order to solve the clinical application problems of existing rehabilitation robots, this paper made a local and global analysis and put forward a new design for the lower limb rehabilitation robot based on the technology of Body Weight Support Treadmill Training(BWSTT). Contrast to others, the robot has features of flexible structure, simple operation, strong practicality and low price. Methods of modular design and intensive design which usually used in Industrial Design were used in this paper, they can solve many clinical difficulties. Through preliminary clinical experiments, the design can solve and improve some problems, but it also need in-depth study and analyze.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130591327","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485407
P. Wong, Hang-Cheong Wong, C. Vong
Fuel efficiency and pollution reduction relate closely to air-ratio (i.e. lambda) among all of the automotive engine control variables. Accurate lambda prediction is essential for effective lambda control. This paper presents an online sequential algorithm for relevance vector machine (RVM) to build a time-dependent RVM lambda function which can be continually updated whenever a sample is added to, or removed from, the training dataset. In order to evaluate the effectiveness of the online sequential algorithm, three lambda time series obtained from experiments under different engine operating conditions were employed. The prediction results under the online sequential algorithm over unseen cases were compared with those under decremental least-squares support vector machine. From the experiments, the online sequential RVM shows promising results and is superior to the typical online algorithm.
{"title":"Modelling and prediction of automotive engine airratio using relevance vector machine","authors":"P. Wong, Hang-Cheong Wong, C. Vong","doi":"10.1109/ICARCV.2012.6485407","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485407","url":null,"abstract":"Fuel efficiency and pollution reduction relate closely to air-ratio (i.e. lambda) among all of the automotive engine control variables. Accurate lambda prediction is essential for effective lambda control. This paper presents an online sequential algorithm for relevance vector machine (RVM) to build a time-dependent RVM lambda function which can be continually updated whenever a sample is added to, or removed from, the training dataset. In order to evaluate the effectiveness of the online sequential algorithm, three lambda time series obtained from experiments under different engine operating conditions were employed. The prediction results under the online sequential algorithm over unseen cases were compared with those under decremental least-squares support vector machine. From the experiments, the online sequential RVM shows promising results and is superior to the typical online algorithm.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123600857","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485283
Kit Yan Chan, S. Nordholm, K. Yiu
Speech recognition has been used in various real-world applications such as automotive control, electronic toys, electronic appliances etc. In many applications involved speech control functions, a commercial speech recognizer is used to identify the speech commands voiced out by the users and the recognized command is used to perform appropriate operations. However, users' commands are often corrupted by surrounding ambient noise. It decreases the effectiveness of speech recognition in order to implement the commands accurately. This paper proposes a multichannel filter to enhance noisy speech commands, in order to improve accuracy of commercial speech recognizers which work under noisy environment. An innovative particle swarm optimization (PSO) is proposed to optimize the parameters of the multichannel filter which intends to improve accuracy of the commercial speech recognizer working under noisy environment. The effectiveness of the multichannel filter was evaluated by interacting with a commercial speech recognizer, which was worked in a warehouse.
{"title":"Multichannel filters for speech recognition using a particle swarm optimization","authors":"Kit Yan Chan, S. Nordholm, K. Yiu","doi":"10.1109/ICARCV.2012.6485283","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485283","url":null,"abstract":"Speech recognition has been used in various real-world applications such as automotive control, electronic toys, electronic appliances etc. In many applications involved speech control functions, a commercial speech recognizer is used to identify the speech commands voiced out by the users and the recognized command is used to perform appropriate operations. However, users' commands are often corrupted by surrounding ambient noise. It decreases the effectiveness of speech recognition in order to implement the commands accurately. This paper proposes a multichannel filter to enhance noisy speech commands, in order to improve accuracy of commercial speech recognizers which work under noisy environment. An innovative particle swarm optimization (PSO) is proposed to optimize the parameters of the multichannel filter which intends to improve accuracy of the commercial speech recognizer working under noisy environment. The effectiveness of the multichannel filter was evaluated by interacting with a commercial speech recognizer, which was worked in a warehouse.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121270524","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485170
Liyong Lin, R. Su, Alin Stefanescu
This paper shows that language based top-down supervisor synthesis of Ramadge-Wonham supervisory control theory is in general not feasible. We show this as a direct consequence of the undecidability result of Decomposable Subset problem (and its prefix closed version), which in turn is a corollary of the undecidability result of Trace Closed Subset problem. Essentially, it is in general not possible to decide in finite amount of time whether there exists a string in a regular language such that all those strings indistinguishable from it are contained in the same language. We bring these results to the attention of control community and investigate the decidability status of some other related problems.
{"title":"Remarks on the difficulty of top-down supervisor synthesis","authors":"Liyong Lin, R. Su, Alin Stefanescu","doi":"10.1109/ICARCV.2012.6485170","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485170","url":null,"abstract":"This paper shows that language based top-down supervisor synthesis of Ramadge-Wonham supervisory control theory is in general not feasible. We show this as a direct consequence of the undecidability result of Decomposable Subset problem (and its prefix closed version), which in turn is a corollary of the undecidability result of Trace Closed Subset problem. Essentially, it is in general not possible to decide in finite amount of time whether there exists a string in a regular language such that all those strings indistinguishable from it are contained in the same language. We bring these results to the attention of control community and investigate the decidability status of some other related problems.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121379413","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485267
S. Khan, N. Mitsou, D. Wollherr, C. Tzafestas
In this paper a novel approach for 3D environment mapping using registered robot poses is presented. The proposed algorithm focuses on improving the quality of robot generated 3D maps by incorporating the uncertainty of 3D points and propagating it into the normal vectors of surfaces. The uncertainty of normal vectors is an indicator of the quality of the detected surface. A controlled random search algorithm is applied to optimize a non-convex function of uncertain normal vectors and number of clusters in order to find the optimal threshold parameter for the segmentation process. This approach leads to an improved cluster coherence and thus better maps.
{"title":"An optimization approach for 3D environment mapping using normal vector uncertainty","authors":"S. Khan, N. Mitsou, D. Wollherr, C. Tzafestas","doi":"10.1109/ICARCV.2012.6485267","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485267","url":null,"abstract":"In this paper a novel approach for 3D environment mapping using registered robot poses is presented. The proposed algorithm focuses on improving the quality of robot generated 3D maps by incorporating the uncertainty of 3D points and propagating it into the normal vectors of surfaces. The uncertainty of normal vectors is an indicator of the quality of the detected surface. A controlled random search algorithm is applied to optimize a non-convex function of uncertain normal vectors and number of clusters in order to find the optimal threshold parameter for the segmentation process. This approach leads to an improved cluster coherence and thus better maps.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"103 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121423455","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485211
Y. Lei, Zhongyi Chu, ShanYong Ren, Dan Li
Various spacecraft missions have driven the need for lighter, stronger deployable structures, which help to hold instruments, such as a magnetometer, away from the spacecraft to avoid the disturbance caused by remanence of the spacecraft body. In this paper, we will present a type of deployable manipulator for small spacecraft, which is characterized by a small stowed volume, light weight and a large magnification ratio. Because the actual parameters of the deployable manipulator are all nonlinear, modeling of the manipulator becomes a key point. Considering the uncertainties in the model parameters, an approximate dynamic model with uncertain parameters is formulated by classifying the uncertainties into different types, including constant parametric, variable parametric and nonparametric uncertainties. Then, a robust adaptive control strategy is proposed to compensate for or reject these uncertainties separately; an output feedback controller is designed to reduce the errors between the desired and the real trajectories, an adaptive controller aims at compensating for constant parametric uncertainties and a robust controller is used to reject the variable parametric and nonparametric model uncertainties. Thus, a robust adaptive control strategy does not rely on the exact dynamic model and can completely compensate for or reject the effect of model uncertainties. Finally, the simulation results show that the proposed control law is perfectly adequate for the deployable manipulator.
{"title":"Dynamic modeling and robust adaptive control of a deployable manipulator","authors":"Y. Lei, Zhongyi Chu, ShanYong Ren, Dan Li","doi":"10.1109/ICARCV.2012.6485211","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485211","url":null,"abstract":"Various spacecraft missions have driven the need for lighter, stronger deployable structures, which help to hold instruments, such as a magnetometer, away from the spacecraft to avoid the disturbance caused by remanence of the spacecraft body. In this paper, we will present a type of deployable manipulator for small spacecraft, which is characterized by a small stowed volume, light weight and a large magnification ratio. Because the actual parameters of the deployable manipulator are all nonlinear, modeling of the manipulator becomes a key point. Considering the uncertainties in the model parameters, an approximate dynamic model with uncertain parameters is formulated by classifying the uncertainties into different types, including constant parametric, variable parametric and nonparametric uncertainties. Then, a robust adaptive control strategy is proposed to compensate for or reject these uncertainties separately; an output feedback controller is designed to reduce the errors between the desired and the real trajectories, an adaptive controller aims at compensating for constant parametric uncertainties and a robust controller is used to reject the variable parametric and nonparametric model uncertainties. Thus, a robust adaptive control strategy does not rely on the exact dynamic model and can completely compensate for or reject the effect of model uncertainties. Finally, the simulation results show that the proposed control law is perfectly adequate for the deployable manipulator.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"247 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114629029","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485352
R. Mehra, S. Satpute, F. Kazi, Navdeep M. Singh
In this paper, a new method is proposed for controller design for a class of stochastic underactuated mechanical system. A controller is designed for stochastic double integrator system derived by backstepping procedure and the idea is to cancel noise at its source without allowing it to enter the system dynamics. The proposed control strategy is then applied to stochastic underactuated mechanical system. We represent actuated dynamics in the stochastic double integrator form. This approach was found to be suitable for cancellation of multiplicative noise influencing actuated coordinates of the system. The effectiveness of the proposed control law is tested on the stochastic SpiderCrane model with underactuation of degree one.
{"title":"Passivity based control of stochastic mechanical system","authors":"R. Mehra, S. Satpute, F. Kazi, Navdeep M. Singh","doi":"10.1109/ICARCV.2012.6485352","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485352","url":null,"abstract":"In this paper, a new method is proposed for controller design for a class of stochastic underactuated mechanical system. A controller is designed for stochastic double integrator system derived by backstepping procedure and the idea is to cancel noise at its source without allowing it to enter the system dynamics. The proposed control strategy is then applied to stochastic underactuated mechanical system. We represent actuated dynamics in the stochastic double integrator form. This approach was found to be suitable for cancellation of multiplicative noise influencing actuated coordinates of the system. The effectiveness of the proposed control law is tested on the stochastic SpiderCrane model with underactuation of degree one.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124434476","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485335
A. Moughlbay, E. Cervera, P. Martinet
When applying service robotic tasks using sensor based control, a classical exponential decrease of the error is usually used in the control laws which can reduces the performance of the executed task. In fact, due to this choice, the convergence time greatly increases especially at the end of the process. To ameliorate the performance of such tasks, we present in this paper two new error regulation strategies to accelerate the service tasks execution. These propositions are compared with the classical one in the case of performing autonomous object's manipulation tasks using real-time visual servoing. The Model Based Tracking method is used to apply head servoing and grasping of different objects using Nao humanoid robot.
{"title":"Error regulation strategies for Model Based visual servoing tasks: Application to autonomous object grasping with Nao robot","authors":"A. Moughlbay, E. Cervera, P. Martinet","doi":"10.1109/ICARCV.2012.6485335","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485335","url":null,"abstract":"When applying service robotic tasks using sensor based control, a classical exponential decrease of the error is usually used in the control laws which can reduces the performance of the executed task. In fact, due to this choice, the convergence time greatly increases especially at the end of the process. To ameliorate the performance of such tasks, we present in this paper two new error regulation strategies to accelerate the service tasks execution. These propositions are compared with the classical one in the case of performing autonomous object's manipulation tasks using real-time visual servoing. The Model Based Tracking method is used to apply head servoing and grasping of different objects using Nao humanoid robot.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124006445","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 : 2012-12-01DOI: 10.1109/ICARCV.2012.6485303
Jie Hou, Yaobin Mao, Jinsheng Sun
Recently, visual tracking has been formulated as a classification problem whose task is detecting the object form the scene with a binary classifier. And online boosting, which adapts the binary classifier to appearance changes by online feature selection, has been investigated by researchers. However, online boosting generally suffers from drifting if the tracking error accumulates. To reduce tracking error, separability-maximum boosting (SMBoost), together with a two stage online boosting paradigm (online SMBoost), is proposed and applied to visual tracking. SMBoost uses a separability based cost function that defined on the statistics. And online boosting is therefore split into two individual stages: online statistics estimating and separability-maximum classifier training. Experiment on UCI machine learning datasets shows that SMBoost is more accurate than batch AdaBoost and its online variation. And benchmark on public sequences indicates that feature selection with online SMBoost is more effective and robust comparing with previous online boosting algorithm. To track a visual object stably, online SMBoost saves more than 50% classifier complexity, and achieves 108 fps.
{"title":"Visual tracking by separability-maximum online boosting","authors":"Jie Hou, Yaobin Mao, Jinsheng Sun","doi":"10.1109/ICARCV.2012.6485303","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485303","url":null,"abstract":"Recently, visual tracking has been formulated as a classification problem whose task is detecting the object form the scene with a binary classifier. And online boosting, which adapts the binary classifier to appearance changes by online feature selection, has been investigated by researchers. However, online boosting generally suffers from drifting if the tracking error accumulates. To reduce tracking error, separability-maximum boosting (SMBoost), together with a two stage online boosting paradigm (online SMBoost), is proposed and applied to visual tracking. SMBoost uses a separability based cost function that defined on the statistics. And online boosting is therefore split into two individual stages: online statistics estimating and separability-maximum classifier training. Experiment on UCI machine learning datasets shows that SMBoost is more accurate than batch AdaBoost and its online variation. And benchmark on public sequences indicates that feature selection with online SMBoost is more effective and robust comparing with previous online boosting algorithm. To track a visual object stably, online SMBoost saves more than 50% classifier complexity, and achieves 108 fps.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124083837","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：