Pub Date : 2012-12-01DOI: 10.1109/ICARCV.2012.6485441
Kazuhiro Kosuge
Mechanical parking systems, such as elevator/tower parking systems, convey parking systems, shuttle parking systems, etc., are very popular in Japan especially inside of a crowded city. These systems are used to park automobiles efficiently for department stores, hotels, etc., although users are required to maneuver their cars skillfully and locate their cars at a specified narrow place. iCART (Intelligent Cooperative Autonomous Robot Transporters) is a robot system which maneuvers a car in a narrow space instead of its driver. Coordination of multiple mobile robots for handling a vehicle is a challenging task for multiple mobile robots. The slippage between a mobile base and the ground is inevitable and its odometry could not be used for the coordination of the multiple robots having physical interaction. The estimation error of robot pose caused by the slippage could damage the automobile carried by the system. A new coordinated motion control scheme has been designed inspired by a “caster” mechanism and implemented in the robots to overcome the problem. Through the development of iCART, we will discuss issues relating to robotics as systems integration.
{"title":"iCART: Intelligent Cooperative Autonomous Robot Transporters","authors":"Kazuhiro Kosuge","doi":"10.1109/ICARCV.2012.6485441","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485441","url":null,"abstract":"Mechanical parking systems, such as elevator/tower parking systems, convey parking systems, shuttle parking systems, etc., are very popular in Japan especially inside of a crowded city. These systems are used to park automobiles efficiently for department stores, hotels, etc., although users are required to maneuver their cars skillfully and locate their cars at a specified narrow place. iCART (Intelligent Cooperative Autonomous Robot Transporters) is a robot system which maneuvers a car in a narrow space instead of its driver. Coordination of multiple mobile robots for handling a vehicle is a challenging task for multiple mobile robots. The slippage between a mobile base and the ground is inevitable and its odometry could not be used for the coordination of the multiple robots having physical interaction. The estimation error of robot pose caused by the slippage could damage the automobile carried by the system. A new coordinated motion control scheme has been designed inspired by a “caster” mechanism and implemented in the robots to overcome the problem. Through the development of iCART, we will discuss issues relating to robotics as systems integration.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"214 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":"132112590","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.2012.6485232
D. Moratuwage, B. Vo, Danwei W. Wang, Han Wang
In this paper we present a novel solution to the Multi-Vehicle SLAM (MVSLAM) problem by extending the random finite set (RFS) based SLAM filter framework using two recently developed multi-sensor information fusion approaches. Our solution is based on the modelling of the measurements and the landmark map as RFSs and factorizing the MVSLAM posterior into a product of the joint vehicle trajectories posterior and the landmark map posterior conditioned the vehicle trajectories. The joint vehicle trajectories posterior is propagated using a particle filter while the landmark map posterior conditioned on the vehicle trajectories is propagated using a Gaussian Mixture (GM) implementation of the probability hypothesis density (PHD) filter.
{"title":"Extending Bayesian RFS SLAM to multi-vehicle SLAM","authors":"D. Moratuwage, B. Vo, Danwei W. Wang, Han Wang","doi":"10.1109/ICARCV.2012.6485232","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485232","url":null,"abstract":"In this paper we present a novel solution to the Multi-Vehicle SLAM (MVSLAM) problem by extending the random finite set (RFS) based SLAM filter framework using two recently developed multi-sensor information fusion approaches. Our solution is based on the modelling of the measurements and the landmark map as RFSs and factorizing the MVSLAM posterior into a product of the joint vehicle trajectories posterior and the landmark map posterior conditioned the vehicle trajectories. The joint vehicle trajectories posterior is propagated using a particle filter while the landmark map posterior conditioned on the vehicle trajectories is propagated using a Gaussian Mixture (GM) implementation of the probability hypothesis density (PHD) filter.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"2 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114037126","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.2012.6485149
A. Matveev, Michael Hoy, A. Savkin
We consider the problem of reactively navigating an unmanned vehicle along an obstacle in the case where data about its boundary are limited to the distance along and the reflection angle of the ray perpendicular to the vehicle centerline. Such situation holds if e.g., the measurements are supplied by several range sensors rigidly mounted at nearly right angles. A sliding mode control law is proposed that drives the vehicle at a pre-specified distance from the boundary and maintains this distance afterwards. This is achieved without estimation of the boundary curvature and holds for obstacles with both convexities and concavities. Mathematically rigorous analysis of the proposed control law is provided, including explicit account for the global geometry of the obstacle. Computer simulations and experiments with real wheeled robots confirm the applicability and performance of the proposed guidance approach.
{"title":"Boundary tracking by a wheeled robot with rigidly mounted sensors","authors":"A. Matveev, Michael Hoy, A. Savkin","doi":"10.1109/ICARCV.2012.6485149","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485149","url":null,"abstract":"We consider the problem of reactively navigating an unmanned vehicle along an obstacle in the case where data about its boundary are limited to the distance along and the reflection angle of the ray perpendicular to the vehicle centerline. Such situation holds if e.g., the measurements are supplied by several range sensors rigidly mounted at nearly right angles. A sliding mode control law is proposed that drives the vehicle at a pre-specified distance from the boundary and maintains this distance afterwards. This is achieved without estimation of the boundary curvature and holds for obstacles with both convexities and concavities. Mathematically rigorous analysis of the proposed control law is provided, including explicit account for the global geometry of the obstacle. Computer simulations and experiments with real wheeled robots confirm the applicability and performance of the proposed guidance approach.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"26 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":"115523387","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.2012.6485190
Aymen Sellaouti, H. Rojbani, A. Hamouda, Cédric Wemmert, A. Deruyver
A hierarchical classification based road extraction approach is proposed in this paper. In order to extract road network, a spectral based-classification associates a confidence score to each region in the image. This score is used to extract road region and its constraints for each iteration of the hierarchy. Road localization is based on Radon transform and expert knowledge. The quality assessments in urban area images show the benefits of the introduced approach.
{"title":"Hierarchical classification-based radon road extraction (HCBRRE)","authors":"Aymen Sellaouti, H. Rojbani, A. Hamouda, Cédric Wemmert, A. Deruyver","doi":"10.1109/ICARCV.2012.6485190","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485190","url":null,"abstract":"A hierarchical classification based road extraction approach is proposed in this paper. In order to extract road network, a spectral based-classification associates a confidence score to each region in the image. This score is used to extract road region and its constraints for each iteration of the hierarchy. Road localization is based on Radon transform and expert knowledge. The quality assessments in urban area images show the benefits of the introduced approach.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"192 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":"116101434","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.2012.6485418
R. Chi, Tao Su, S. Jin
In this paper, an iterative learning control approach is developed for a class of uncertainty nonlinear discrete-time systems based on the identification of the controlled system. At first, the linearized model of the nonlinear system is proposed. And then using the identification method, we present an indirect iterative learning control scheme for the controlled system. Analysis shows that the scheme can guarantee the system convergence under some conditions.
{"title":"An identification based indirect iterative learning control via data-driven approach","authors":"R. Chi, Tao Su, S. Jin","doi":"10.1109/ICARCV.2012.6485418","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485418","url":null,"abstract":"In this paper, an iterative learning control approach is developed for a class of uncertainty nonlinear discrete-time systems based on the identification of the controlled system. At first, the linearized model of the nonlinear system is proposed. And then using the identification method, we present an indirect iterative learning control scheme for the controlled system. Analysis shows that the scheme can guarantee the system convergence under some conditions.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"1 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":"122784300","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.2012.6485409
Zhixin Yang, Difu Xiao
3D shape reuse, as an effective way to carry out innovative design, requires a digital model database where the entities are accurate and sufficient representations of objects in the real world. 3D scanning is a prevailing tool to quickly convert physical models into virtual ones. However, the scanned models without post-processing could not be used directly due to environment noise and accuracy limitation in terms of discrete sampling property in scanning. This paper introduces a systemic point-cloud de-noising and mesh smoothing method to handle this issue. The model de-noising and regularity is based on k-means clustering, and mesh smoothing module is an improved mean approach which processes the discrete data in the regular order. Case study will be given to verify the smoothing effectiveness. The proposed method could facilitate the construction of model database for design reuse, and could be output to downstream applications such as shape adaptive deformation, and shape searching.
{"title":"A systemic point-cloud de-noising and smoothing method for 3D shape reuse","authors":"Zhixin Yang, Difu Xiao","doi":"10.1109/ICARCV.2012.6485409","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485409","url":null,"abstract":"3D shape reuse, as an effective way to carry out innovative design, requires a digital model database where the entities are accurate and sufficient representations of objects in the real world. 3D scanning is a prevailing tool to quickly convert physical models into virtual ones. However, the scanned models without post-processing could not be used directly due to environment noise and accuracy limitation in terms of discrete sampling property in scanning. This paper introduces a systemic point-cloud de-noising and mesh smoothing method to handle this issue. The model de-noising and regularity is based on k-means clustering, and mesh smoothing module is an improved mean approach which processes the discrete data in the regular order. Case study will be given to verify the smoothing effectiveness. The proposed method could facilitate the construction of model database for design reuse, and could be output to downstream applications such as shape adaptive deformation, and shape searching.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"4 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":"123754307","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.2012.6485177
Tushar Jain, J. Yamé, D. Sauter
In this paper, we present a case study for fault-tolerant control of an electric circuit in the behavioral framework. First, we demonstrate the modeling of electric circuit using the behavioral point of view, where no a priori input-output partition has been made. The uniqueness of behavioral approach lies in the fact that it deals only with variables describing the system without any dedicated (external or internal-type) representation. Taking this point of view, we present a novel real-time fault-tolerant control strategy, which does not require an explicit model-based fault diagnosis unit. Instead, the controller is reconfigured online directly based on the system trajectories, and the given control specifications. In this way, we inherently excrete the shortcomings that are often seen in model-based fault-tolerant systems.
{"title":"Case study on behavioral approach to fault-tolerant control: Application to an electric circuit","authors":"Tushar Jain, J. Yamé, D. Sauter","doi":"10.1109/ICARCV.2012.6485177","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485177","url":null,"abstract":"In this paper, we present a case study for fault-tolerant control of an electric circuit in the behavioral framework. First, we demonstrate the modeling of electric circuit using the behavioral point of view, where no a priori input-output partition has been made. The uniqueness of behavioral approach lies in the fact that it deals only with variables describing the system without any dedicated (external or internal-type) representation. Taking this point of view, we present a novel real-time fault-tolerant control strategy, which does not require an explicit model-based fault diagnosis unit. Instead, the controller is reconfigured online directly based on the system trajectories, and the given control specifications. In this way, we inherently excrete the shortcomings that are often seen in model-based fault-tolerant systems.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"8 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":"123943890","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.2012.6485411
Hongliang Yu, Wanli Liu, Huijun Dong
The calciner link and grate cooler link in the cement production have the characteristics of strong nonlinearity, time-varying, large time delay and coupling among variables which cause the big fluctuation of working condition, increasing difficulty of modeling and control. To solve such problem, we propose the working condition identification method based on expert system. In this paper, according to real-time and accuracy control requirements and the site operation experience, we summarize the working condition identification expert rules for calciner and grate cooler links. Then according to the different features of different working conditions, we take different identification methods to recognize working conditions. Based on the above expert knowledge, working condition recognition system can identify the current condition accurately and give reasonable operation suggestions. Condition recognition software is compiled by VB6.0, and field application shows that the project is reasonable and practical.
{"title":"Research on recognition of working condition for calciner and grate cooler based on expert system","authors":"Hongliang Yu, Wanli Liu, Huijun Dong","doi":"10.1109/ICARCV.2012.6485411","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485411","url":null,"abstract":"The calciner link and grate cooler link in the cement production have the characteristics of strong nonlinearity, time-varying, large time delay and coupling among variables which cause the big fluctuation of working condition, increasing difficulty of modeling and control. To solve such problem, we propose the working condition identification method based on expert system. In this paper, according to real-time and accuracy control requirements and the site operation experience, we summarize the working condition identification expert rules for calciner and grate cooler links. Then according to the different features of different working conditions, we take different identification methods to recognize working conditions. Based on the above expert knowledge, working condition recognition system can identify the current condition accurately and give reasonable operation suggestions. Condition recognition software is compiled by VB6.0, and field application shows that the project is reasonable and practical.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"28 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":"125504690","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.2012.6485328
Mingyue Cui, Zhaojing Wu, Xue‐Jun Xie
This paper focuses on the problem of adaptive tracking for a class of stochastic mechanical control systems with unknown parameters. By reasonably introducing random noise, a method to construct stochastic Lagrangian control systems is given. Under some milder assumptions, an adaptive tracking controller is designed such that the mean square of the tracking error converges to an arbitrarily small neighborhood of zero by tuning design parameters.
{"title":"Adaptive tracking control for a class of stochastic mechanical systems","authors":"Mingyue Cui, Zhaojing Wu, Xue‐Jun Xie","doi":"10.1109/ICARCV.2012.6485328","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485328","url":null,"abstract":"This paper focuses on the problem of adaptive tracking for a class of stochastic mechanical control systems with unknown parameters. By reasonably introducing random noise, a method to construct stochastic Lagrangian control systems is given. Under some milder assumptions, an adaptive tracking controller is designed such that the mean square of the tracking error converges to an arbitrarily small neighborhood of zero by tuning design parameters.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"120 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":"129583685","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.2012.6485140
Chang Wang, P. Wiggers, K. Hindriks, C. Jonker
We present a modified version of Extended Classifier System (XCS) on a humanoid NAO robot. The robot is capable of learning a complete, accurate, and maximally general map of an environment through evolutionary search and reinforcement learning. The standard alternation between explore and exploit trials is revised so that the robot relearns only when necessary. This modification makes the learning more effective and provides the XCS with external memory to evaluate the environmental change. Furthermore, it overcomes the drawbacks of learning rate settings in traditional XCS. A simple object seeking task is presented which demonstrates the desirable adaptivity of LCS for a sequential task on a real robot in dynamic environments.
{"title":"Learning Classifier System on a humanoid NAO robot in dynamic environments","authors":"Chang Wang, P. Wiggers, K. Hindriks, C. Jonker","doi":"10.1109/ICARCV.2012.6485140","DOIUrl":"https://doi.org/10.1109/ICARCV.2012.6485140","url":null,"abstract":"We present a modified version of Extended Classifier System (XCS) on a humanoid NAO robot. The robot is capable of learning a complete, accurate, and maximally general map of an environment through evolutionary search and reinforcement learning. The standard alternation between explore and exploit trials is revised so that the robot relearns only when necessary. This modification makes the learning more effective and provides the XCS with external memory to evaluate the environmental change. Furthermore, it overcomes the drawbacks of learning rate settings in traditional XCS. A simple object seeking task is presented which demonstrates the desirable adaptivity of LCS for a sequential task on a real robot in dynamic environments.","PeriodicalId":441236,"journal":{"name":"2012 12th International Conference on Control Automation Robotics & Vision (ICARCV)","volume":"8 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":"128037517","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：