Pub Date : 2005-07-18DOI: 10.1109/ICAR.2005.1507422
G. Huang, A. Rad, Y. Wong
In this paper, we propose a novel online algorithm for simultaneous localization and mapping (SLAM) in dynamic environments. We first formulate the problem with two interdependent parts: SLAM and multiple target tracking (MTT). To pursue online performance, we propose a hierarchical hybrid method to solve SLAM: locally by maximum likelihood (ML) with occupancy grid map, and globally by extended Kalman filter (EKF) with feature-based map. Meanwhile we apply a straightforward nearest neighborhood (NN) algorithm based on Euclidean metric to address MTT. In order to track multiple moving objects reliably, we propose an enhanced fuzzy clustering (EFC) method to segment 2D range images and reliably group objects. Experiments validated on Pioneer 2DX mobile robot with SICK LMS200 demonstrate the capability and robustness of the proposed algorithm
{"title":"Online SLAM in dynamic environments","authors":"G. Huang, A. Rad, Y. Wong","doi":"10.1109/ICAR.2005.1507422","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507422","url":null,"abstract":"In this paper, we propose a novel online algorithm for simultaneous localization and mapping (SLAM) in dynamic environments. We first formulate the problem with two interdependent parts: SLAM and multiple target tracking (MTT). To pursue online performance, we propose a hierarchical hybrid method to solve SLAM: locally by maximum likelihood (ML) with occupancy grid map, and globally by extended Kalman filter (EKF) with feature-based map. Meanwhile we apply a straightforward nearest neighborhood (NN) algorithm based on Euclidean metric to address MTT. In order to track multiple moving objects reliably, we propose an enhanced fuzzy clustering (EFC) method to segment 2D range images and reliably group objects. Experiments validated on Pioneer 2DX mobile robot with SICK LMS200 demonstrate the capability and robustness of the proposed algorithm","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128944220","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507462
K. Hoshino, T. Tanimoto
The authors propose a system for searching the posture of human 3D hands and fingers in real time and with high accuracy, without using any special peripheral equipment such as infrared range sensor, PC cluster, etc., by a method of searching similar image quickly with high accuracy from a large volume of image database containing complicated shapes and self-occlusions. In designing the system, we constructed a database to be adaptable even to differences in hand shape among individuals, and searched computer graphics (CG) images of hand similar to unknown hand image input, through extraction of characteristics using high-order local autocorrelational patterns, reduction of the amount of characteristics centering on principal component analysis, and prior rearrangement of data corresponding to the amount of characteristics. As a result of experiments, our system carried out high-accuracy estimation of human hand shape with the processing speed of 30 fps or over
{"title":"High-speed search for similar image from database for dexterous robot hand control","authors":"K. Hoshino, T. Tanimoto","doi":"10.1109/ICAR.2005.1507462","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507462","url":null,"abstract":"The authors propose a system for searching the posture of human 3D hands and fingers in real time and with high accuracy, without using any special peripheral equipment such as infrared range sensor, PC cluster, etc., by a method of searching similar image quickly with high accuracy from a large volume of image database containing complicated shapes and self-occlusions. In designing the system, we constructed a database to be adaptable even to differences in hand shape among individuals, and searched computer graphics (CG) images of hand similar to unknown hand image input, through extraction of characteristics using high-order local autocorrelational patterns, reduction of the amount of characteristics centering on principal component analysis, and prior rearrangement of data corresponding to the amount of characteristics. As a result of experiments, our system carried out high-accuracy estimation of human hand shape with the processing speed of 30 fps or over","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127918939","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507514
P. Nebot, E. Cervera
The advances in mobile robotics, computing power, and wireless communications have turned feasible the development of communities of autonomous robots. In the last years, there is a greater interest in systems of multiple autonomous robots for the accomplishment of cooperative tasks. This project takes it into account and presents an architecture for the development of collaborative applications for a heterogeneous team of mobile robots based on embedded agents. The implemented architecture has the capacity to allow the team of robots to accomplish such tasks, and also it has tools and features that allow programmers to develop complex applications in a reasonable time. An agent-based development platform has been used for this purpose, due to it integrates the necessary capabilities for developing distributed applications, and manages the communications among all the components. To demonstrate the advantages of the architecture a real application, robot following, has been implemented. It consists of a set of embedded agents, which run in real robot systems, demonstrating that embedding agents in distributed intelligent systems is a powerful method for quick application development in the multirobot domain
{"title":"A framework for the development of cooperative robotic applications","authors":"P. Nebot, E. Cervera","doi":"10.1109/ICAR.2005.1507514","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507514","url":null,"abstract":"The advances in mobile robotics, computing power, and wireless communications have turned feasible the development of communities of autonomous robots. In the last years, there is a greater interest in systems of multiple autonomous robots for the accomplishment of cooperative tasks. This project takes it into account and presents an architecture for the development of collaborative applications for a heterogeneous team of mobile robots based on embedded agents. The implemented architecture has the capacity to allow the team of robots to accomplish such tasks, and also it has tools and features that allow programmers to develop complex applications in a reasonable time. An agent-based development platform has been used for this purpose, due to it integrates the necessary capabilities for developing distributed applications, and manages the communications among all the components. To demonstrate the advantages of the architecture a real application, robot following, has been implemented. It consists of a set of embedded agents, which run in real robot systems, demonstrating that embedding agents in distributed intelligent systems is a powerful method for quick application development in the multirobot domain","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125404976","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507497
J. Ryu, Jong-Hwan Kim
Recently proposed stable teleoperation control scheme, based on time domain passivity, is modified to remove several conservatisms. During unconstrained motion and contacting with soft and deformable environments, the two-port time domain passivity approach (Ryu et al., 2004) was excessively dissipating energy even though it was stable without any energy dissipation. The main reason of this conservatism is on the fact that the time domain passivity controller does not include the external energy dissipation elements at the slave manipulator. The measured interaction force between slave and environment allow the time domain passivity observer to include the amount of energy dissipation of the slave manipulator to the monitored energy. With the modified passivity observer, reference energy following idea (Ryu, et al., 2003) is applied to satisfy the passivity condition. The feasibility of the developed methods is proved with experiments. Improved performance is obtained in unconstrained motion and contacting with a soft environment
对最近提出的基于时域无源的稳定遥操作控制方案进行了改进，去掉了几个保守性。在无约束运动和与软、可变形环境接触时，双端口时域无源方法(Ryu et al.， 2004)虽然稳定且无任何能量耗散，但存在过度耗散能量的问题。这种保守性的主要原因是时域无源控制器没有考虑从机械臂处的外部能量耗散因素。测量的从机与环境之间的相互作用力允许时域被动观测器将从机的能量耗散量计入监测的能量。在改进的被动观测器中，采用参考能量跟随思想(Ryu, et al.， 2003)来满足被动条件。实验证明了所提方法的可行性。在无约束运动和与软环境接触时，系统的性能得到了提高
{"title":"Stable and high performance teleoperation with time domain passivity control: reference energy following scheme","authors":"J. Ryu, Jong-Hwan Kim","doi":"10.1109/ICAR.2005.1507497","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507497","url":null,"abstract":"Recently proposed stable teleoperation control scheme, based on time domain passivity, is modified to remove several conservatisms. During unconstrained motion and contacting with soft and deformable environments, the two-port time domain passivity approach (Ryu et al., 2004) was excessively dissipating energy even though it was stable without any energy dissipation. The main reason of this conservatism is on the fact that the time domain passivity controller does not include the external energy dissipation elements at the slave manipulator. The measured interaction force between slave and environment allow the time domain passivity observer to include the amount of energy dissipation of the slave manipulator to the monitored energy. With the modified passivity observer, reference energy following idea (Ryu, et al., 2003) is applied to satisfy the passivity condition. The feasibility of the developed methods is proved with experiments. Improved performance is obtained in unconstrained motion and contacting with a soft environment","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123247777","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507388
Eunjung Kim, Y. Youm
In this paper, we show the simulation result to find the suitable fish swimming modes (specially BCF swimming) for fish like underwater robot system. To find the suitable swimming modes, we assume that they have the same length, volume, and weight, but the different numbers of actuator (joint). And we use the minimum number of the joint for each swimming mode. We derive the dynamic equation for each system using Kane's method and these results are compared by DADS. We present the optimal solution of swimming mode for some aquatic locomotion, especially faster(high propulsive efficiency) and more maneuverable (quick turning motion)
{"title":"Simulation study of fish swimming modes for aquatic robot system","authors":"Eunjung Kim, Y. Youm","doi":"10.1109/ICAR.2005.1507388","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507388","url":null,"abstract":"In this paper, we show the simulation result to find the suitable fish swimming modes (specially BCF swimming) for fish like underwater robot system. To find the suitable swimming modes, we assume that they have the same length, volume, and weight, but the different numbers of actuator (joint). And we use the minimum number of the joint for each swimming mode. We derive the dynamic equation for each system using Kane's method and these results are compared by DADS. We present the optimal solution of swimming mode for some aquatic locomotion, especially faster(high propulsive efficiency) and more maneuverable (quick turning motion)","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122268678","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507389
V. Creuze, B. Jouvencel, P. Baccou
Navigation of autonomous underwater vehicles (A.U.V.) in very shallow waters implies acoustic detection. In single beam sonar systems, sound emitted by ultrasonic transducers is diffracted and secondary lobes appear. Considering the sea bottom's backscattering properties, secondary lobes can be used to work out the three-dimensional equation of the plane that represents the seabed. In this paper, we first consider characteristics of electro-acoustic transducers with rectangular aperture and study the resulting acoustic diffraction. Then, we explain how to choose the best dimensions of the transducer and the related best orientation. Moreover, we introduce a method aiming to extract the seabed 3D equation from the received acoustic echo. Thus single beam sonar systems can be used for bottom tracking purposes. We present the results of our simulations and our experimental device
{"title":"3D-bottom tracking based on acoustic diffraction for autonomous underwater vehicles","authors":"V. Creuze, B. Jouvencel, P. Baccou","doi":"10.1109/ICAR.2005.1507389","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507389","url":null,"abstract":"Navigation of autonomous underwater vehicles (A.U.V.) in very shallow waters implies acoustic detection. In single beam sonar systems, sound emitted by ultrasonic transducers is diffracted and secondary lobes appear. Considering the sea bottom's backscattering properties, secondary lobes can be used to work out the three-dimensional equation of the plane that represents the seabed. In this paper, we first consider characteristics of electro-acoustic transducers with rectangular aperture and study the resulting acoustic diffraction. Then, we explain how to choose the best dimensions of the transducer and the related best orientation. Moreover, we introduce a method aiming to extract the seabed 3D equation from the received acoustic echo. Thus single beam sonar systems can be used for bottom tracking purposes. We present the results of our simulations and our experimental device","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"19 27","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120927732","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507483
R. Héliot, B. Espiau, F. Favre-Reguilion
Using microsensors for the robust and accurate analysis of human posture or gait is an interesting opportunity for rehabilitation and robotics applications. This paper describes a feasibility study in which the possibility of using a new type of embedded microsensors, based on the coupling of accelerometers and magnetometers, and developed by CEA/LETI is investigated. This study consists in identifying what part of the gait cycle is active by using a reconstruction of the knee joint angle by two microsensors fixed on tibia and thigh, during a steady-state sagittal walk. More than just an identification of a few gait states, this approach allows us to continuously extract the current position on the gait cycle. We compare the reconstructed knee joint angle with a stored reference taking into account uncertainties on the velocity and perturbations of the terrestrial magnetic field. To accurately identify the phase of the gait movement, we fuse different simple and complementary methods: morphomathematics, cyclogram analysis, wavelet transform, qualitative analysis, crosscorrelation. These results encourage us to extend this work to explore the possibility of recognition of a larger set of human movements using more sensors and improved algorithms of signal processing
{"title":"Continuous identification of gait phase for robotics and rehabilitation using microsensors","authors":"R. Héliot, B. Espiau, F. Favre-Reguilion","doi":"10.1109/ICAR.2005.1507483","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507483","url":null,"abstract":"Using microsensors for the robust and accurate analysis of human posture or gait is an interesting opportunity for rehabilitation and robotics applications. This paper describes a feasibility study in which the possibility of using a new type of embedded microsensors, based on the coupling of accelerometers and magnetometers, and developed by CEA/LETI is investigated. This study consists in identifying what part of the gait cycle is active by using a reconstruction of the knee joint angle by two microsensors fixed on tibia and thigh, during a steady-state sagittal walk. More than just an identification of a few gait states, this approach allows us to continuously extract the current position on the gait cycle. We compare the reconstructed knee joint angle with a stored reference taking into account uncertainties on the velocity and perturbations of the terrestrial magnetic field. To accurately identify the phase of the gait movement, we fuse different simple and complementary methods: morphomathematics, cyclogram analysis, wavelet transform, qualitative analysis, crosscorrelation. These results encourage us to extend this work to explore the possibility of recognition of a larger set of human movements using more sensors and improved algorithms of signal processing","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122527327","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507441
Wael AbdAlmageed, B. J. Burns, Larry S. Davis
This paper presents a new human-motion identification and segmentation algorithm, for mobile robot platforms. The algorithm is based on computing the alignment error between pairs of object images acquired from a moving platform. Pairs of images generating relatively small alignment errors are used to estimate the fundamental frequency of the object's motion. A decision criterion is then used to test the significance of the estimated frequency and to classify the object's motion. To verify the validity of the proposed approach, experimental results are shown on different classes of objects
{"title":"Identifying and segmenting human-motion for mobile robot navigation using alignment errors","authors":"Wael AbdAlmageed, B. J. Burns, Larry S. Davis","doi":"10.1109/ICAR.2005.1507441","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507441","url":null,"abstract":"This paper presents a new human-motion identification and segmentation algorithm, for mobile robot platforms. The algorithm is based on computing the alignment error between pairs of object images acquired from a moving platform. Pairs of images generating relatively small alignment errors are used to estimate the fundamental frequency of the object's motion. A decision criterion is then used to test the significance of the estimated frequency and to classify the object's motion. To verify the validity of the proposed approach, experimental results are shown on different classes of objects","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133741158","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507412
G. Gogu
In this paper we present a new family of singularity-free fully-isotropic parallel manipulators with Schonflies motions. The moving platform of a parallel manipulator with Schonflies motions (PMSM) has four degrees of freedom, which are three independent translations and one rotation about an axis of fixed direction. A method is proposed for structural synthesis of fully-isotropic PMSMs based on the theory of linear transformations. A one-to-one correspondence exists between the actuated joint velocity space and the external velocity space of the moving platform. The Jacobian matrix mapping the two vector spaces of fully-isotropic PMSMs presented in this paper is the identity 4times4 matrix throughout the entire workspace. The condition number and the determinant of the Jacobian matrix being equal to one, the manipulator performs very well with regard to force and motion transmission capabilities. As far as we are aware, the family of 8750 solutions of singularity-free fully-isotropic PMSMs introduced in this paper is presented for the first time in the literature. These solutions are derived from a family of PMSMs with decoupled motions and elementary legs also presented for the first time
{"title":"Singularity-free fully-isotropic parallel manipulators with Schonflies motions","authors":"G. Gogu","doi":"10.1109/ICAR.2005.1507412","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507412","url":null,"abstract":"In this paper we present a new family of singularity-free fully-isotropic parallel manipulators with Schonflies motions. The moving platform of a parallel manipulator with Schonflies motions (PMSM) has four degrees of freedom, which are three independent translations and one rotation about an axis of fixed direction. A method is proposed for structural synthesis of fully-isotropic PMSMs based on the theory of linear transformations. A one-to-one correspondence exists between the actuated joint velocity space and the external velocity space of the moving platform. The Jacobian matrix mapping the two vector spaces of fully-isotropic PMSMs presented in this paper is the identity 4times4 matrix throughout the entire workspace. The condition number and the determinant of the Jacobian matrix being equal to one, the manipulator performs very well with regard to force and motion transmission capabilities. As far as we are aware, the family of 8750 solutions of singularity-free fully-isotropic PMSMs introduced in this paper is presented for the first time in the literature. These solutions are derived from a family of PMSMs with decoupled motions and elementary legs also presented for the first time","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133086309","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 : 2005-07-18DOI: 10.1109/ICAR.2005.1507477
A. Bohori, K. Venkatesh, Vinay Singh, A. Mukerjee
Optical flow based navigation systems depend on the planar navigation constraint, which reduces search to two parameters-translation velocity in the headed direction and the rotational velocity about vertical axis. However, this constraint often fails in practice when motion undulations caused by floor variations or wheel kinematics generate dominating vertical flows, resulting in widely erroneous depth maps. In this work, these floor undulations are modeled as rotations about an axis derivable from the robot kinematics. These are then dynamically calibrated and compensated for, resulting in more accurate depth maps. Optical flow is now computed using the so called generalized dynamic image model [S. Negahdaripour, 1998] which results in a much less noisy depth map. Using fuzzy inference to ameliorate the effects of noise added in the differentiation process, we show an implementation on a Pioneer-II mobile robot that navigates successfully in unknown cluttered static environments
{"title":"Visual navigation of wheeled robots : compensating floor undulations","authors":"A. Bohori, K. Venkatesh, Vinay Singh, A. Mukerjee","doi":"10.1109/ICAR.2005.1507477","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507477","url":null,"abstract":"Optical flow based navigation systems depend on the planar navigation constraint, which reduces search to two parameters-translation velocity in the headed direction and the rotational velocity about vertical axis. However, this constraint often fails in practice when motion undulations caused by floor variations or wheel kinematics generate dominating vertical flows, resulting in widely erroneous depth maps. In this work, these floor undulations are modeled as rotations about an axis derivable from the robot kinematics. These are then dynamically calibrated and compensated for, resulting in more accurate depth maps. Optical flow is now computed using the so called generalized dynamic image model [S. Negahdaripour, 1998] which results in a much less noisy depth map. Using fuzzy inference to ameliorate the effects of noise added in the differentiation process, we show an implementation on a Pioneer-II mobile robot that navigates successfully in unknown cluttered static environments","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2005-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115082644","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：