Pub Date : 2005-07-18DOI: 10.1109/ICAR.2005.1507480
A. Nüchter, K. Lingemann, J. Hertzberg, H. Surmann
This paper presents a novel method for object detection and classification in 3D laser range data that is acquired by an autonomous mobile robot. Unrestricted objects are learned using classification and regression trees (CARTs) and using an Ada Boost learning procedure. Off-screen rendered depth and reflectance images serve as an input for learning. The performance of the classification is improved by combining both sensor modalities, which are independent from external light. This enables highly accurate, fast and reliable 3D object localization with point matching. Competitive learning is used for evaluating the accuracy of the object localization
{"title":"Accurate object localization in 3D laser range scans","authors":"A. Nüchter, K. Lingemann, J. Hertzberg, H. Surmann","doi":"10.1109/ICAR.2005.1507480","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507480","url":null,"abstract":"This paper presents a novel method for object detection and classification in 3D laser range data that is acquired by an autonomous mobile robot. Unrestricted objects are learned using classification and regression trees (CARTs) and using an Ada Boost learning procedure. Off-screen rendered depth and reflectance images serve as an input for learning. The performance of the classification is improved by combining both sensor modalities, which are independent from external light. This enables highly accurate, fast and reliable 3D object localization with point matching. Competitive learning is used for evaluating the accuracy of the object localization","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"45 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":"130145305","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.2005.1507393
Wei Zhao, B. Kim, A. Larson, R. Voyles
Small robots can be beneficial to important applications such as civilian search and rescue and military surveillance, but their limited resources constrain their functionality and performance. To address this, a reconfigurable technique based on field-programmable gate arrays (FPGAs) may be applied, which has the potential for greater functionality and higher performance, but with smaller volume and lower power dissipation. This project investigates an FPGA-based PID motion control system for small, self-adaptive systems. For one channel control, parallel and serial architectures for the PID control algorithm are designed and implemented. Based on these one-channel designs, four architectures for multiple-channel control are proposed and two channel-level serial (CLS) architectures are designed and implemented. Functional correctness of all the designs was verified in motor control experiments, and area, speed, and power consumption were analyzed. The tradeoffs between the different designs are discussed in terms of area, power consumption, and execution time with respect to number of channels, sampling rate, and control clock frequency. The data gathered in this paper will be leveraged in future work to dynamically adapt the robot at run time
{"title":"FPGA implementation of closed-loop control system for small-scale robot","authors":"Wei Zhao, B. Kim, A. Larson, R. Voyles","doi":"10.1109/ICAR.2005.1507393","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507393","url":null,"abstract":"Small robots can be beneficial to important applications such as civilian search and rescue and military surveillance, but their limited resources constrain their functionality and performance. To address this, a reconfigurable technique based on field-programmable gate arrays (FPGAs) may be applied, which has the potential for greater functionality and higher performance, but with smaller volume and lower power dissipation. This project investigates an FPGA-based PID motion control system for small, self-adaptive systems. For one channel control, parallel and serial architectures for the PID control algorithm are designed and implemented. Based on these one-channel designs, four architectures for multiple-channel control are proposed and two channel-level serial (CLS) architectures are designed and implemented. Functional correctness of all the designs was verified in motor control experiments, and area, speed, and power consumption were analyzed. The tradeoffs between the different designs are discussed in terms of area, power consumption, and execution time with respect to number of channels, sampling rate, and control clock frequency. The data gathered in this paper will be leveraged in future work to dynamically adapt the robot at run time","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":"132508588","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.2005.1507418
Y. Sugimoto, K. Osuka
The purpose of this paper is to analyze the stability of passive dynamic walking using an approximate analytical Poincare map of the impact point, which is the state of walking robot at the collision between a swing leg and ground. Especially, in this paper, we focus on the feedback structure in equations which are used to get the Poincare map, and consider the relationship between stability of passive-dynamic-walking and the feedback structure. In this process, we derive a control method of quasi passive-dynamic-walking which utilizes the inner structure of Poincare map and confirm the effectiveness of the control method via several simulations
{"title":"Stability analysis of passive-dynamic-walking focusing on the inner structure of Poincare map","authors":"Y. Sugimoto, K. Osuka","doi":"10.1109/ICAR.2005.1507418","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507418","url":null,"abstract":"The purpose of this paper is to analyze the stability of passive dynamic walking using an approximate analytical Poincare map of the impact point, which is the state of walking robot at the collision between a swing leg and ground. Especially, in this paper, we focus on the feedback structure in equations which are used to get the Poincare map, and consider the relationship between stability of passive-dynamic-walking and the feedback structure. In this process, we derive a control method of quasi passive-dynamic-walking which utilizes the inner structure of Poincare map and confirm the effectiveness of the control method via several simulations","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"32 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":"131856590","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.2005.1507397
Jian Yang, Z. Qu, Jing Wang, R. Hull
In this paper, an approach is proposed to determine real-time an optimized and collision-free path for a fixed wing flying vehicle moving in a dynamically changing 3D space. In the algorithm, boundary conditions, kinematic constraints, and collision avoidance criteria are explicitly considered and satisfied by a family of trajectories parameterized in terms of three polynomials along the primary axes in the 3D space. By doing so, a family of feasible and collision-free paths are found and the final trajectory planned is selected by optimizing a suitable performance index corresponding to a near-shortest path. The solution to the optimized path and its associated steering controls are found in closed form so that the solution can be implemented efficiently real time and that the planned trajectory can be also quickly updated as the flying environment changes. The proposed method is validated by computer simulations
{"title":"A real-time optimized path planning for a fixed wing vehicle flying in a dynamic and uncertain environment","authors":"Jian Yang, Z. Qu, Jing Wang, R. Hull","doi":"10.1109/ICAR.2005.1507397","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507397","url":null,"abstract":"In this paper, an approach is proposed to determine real-time an optimized and collision-free path for a fixed wing flying vehicle moving in a dynamically changing 3D space. In the algorithm, boundary conditions, kinematic constraints, and collision avoidance criteria are explicitly considered and satisfied by a family of trajectories parameterized in terms of three polynomials along the primary axes in the 3D space. By doing so, a family of feasible and collision-free paths are found and the final trajectory planned is selected by optimizing a suitable performance index corresponding to a near-shortest path. The solution to the optimized path and its associated steering controls are found in closed form so that the solution can be implemented efficiently real time and that the planned trajectory can be also quickly updated as the flying environment changes. The proposed method is validated by computer simulations","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"26 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":"131950490","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.2005.1507464
Kanglin Xu, G. Luger
In this paper, we describe an algorithm based on a distribution of contours traced by particle moving in directions undergoing Brownian motion for a segmentation problem. We analyze the properties of the affinity matrix, whose elements are the edge-to-edge transition probabilities, from a mathematical point of view and give formal proofs. This analysis is essential because we can use the properties of the affinity matrix to reduce the amount of computation greatly when solving segmentation problems, especially for large real images. The results obtained can be used for robot visual servo to pick multiple objects in the scene
{"title":"Properties of the affinity matrix for multiple closed contour segmentation","authors":"Kanglin Xu, G. Luger","doi":"10.1109/ICAR.2005.1507464","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507464","url":null,"abstract":"In this paper, we describe an algorithm based on a distribution of contours traced by particle moving in directions undergoing Brownian motion for a segmentation problem. We analyze the properties of the affinity matrix, whose elements are the edge-to-edge transition probabilities, from a mathematical point of view and give formal proofs. This analysis is essential because we can use the properties of the affinity matrix to reduce the amount of computation greatly when solving segmentation problems, especially for large real images. The results obtained can be used for robot visual servo to pick multiple objects in the scene","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"30 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":"122350415","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.2005.1507446
M. C. Cavusoglu, Jason Rotella, W. Newman, Sangeun Choi, Jeff Ustin, S. Sastry
Use of intelligent robotic tools promises an alternative and superior way of performing off-pump coronary artery bypass graft (CABG) surgery. In the robotic-assisted surgical paradigm proposed, the conventional surgical tools are replaced with robotic instruments which are under direct control of the surgeon through teleoperation. The robotic tools actively cancel the relative motion between the surgical instruments and the point-of-interest on the beating heart, in contrast to traditional off-pump CABG where the heart is passively constrained to dampen the beating motion. As a result, the surgeon operates on the heart as if it were stationary. We call the proposed algorithm "active relative motion cancelling (ARMC)" to emphasize the active cancellation. In the paper, a model-based intelligent ARMC algorithm is proposed to achieve effective motion cancellation. This is followed by an analysis of local motion of the heart collected using a sonomicrometry system to determine the specifications for ARMC system. Finally, the experimental results of the algorithm implemented on two 1-DOF robotic test-bed systems are reported
{"title":"Control algorithms for active relative motion cancelling for robotic assisted off-pump coronary artery bypass graft surgery","authors":"M. C. Cavusoglu, Jason Rotella, W. Newman, Sangeun Choi, Jeff Ustin, S. Sastry","doi":"10.1109/ICAR.2005.1507446","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507446","url":null,"abstract":"Use of intelligent robotic tools promises an alternative and superior way of performing off-pump coronary artery bypass graft (CABG) surgery. In the robotic-assisted surgical paradigm proposed, the conventional surgical tools are replaced with robotic instruments which are under direct control of the surgeon through teleoperation. The robotic tools actively cancel the relative motion between the surgical instruments and the point-of-interest on the beating heart, in contrast to traditional off-pump CABG where the heart is passively constrained to dampen the beating motion. As a result, the surgeon operates on the heart as if it were stationary. We call the proposed algorithm \"active relative motion cancelling (ARMC)\" to emphasize the active cancellation. In the paper, a model-based intelligent ARMC algorithm is proposed to achieve effective motion cancellation. This is followed by an analysis of local motion of the heart collected using a sonomicrometry system to determine the specifications for ARMC system. Finally, the experimental results of the algorithm implemented on two 1-DOF robotic test-bed systems are reported","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"29 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":"115768129","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.2005.1507507
A. Punning, M. Anton, M. Kruusmaa, A. Aabloo
Ion-polymer metal composites (IPMC) are electroactive polymer (EAP) materials that behave in electric field similar to biological muscles. Among the shortcomings of an emerging technology like IPMC muscles their energy consumption is one of the most serious. This paper represents a novel open-loop control method for IPMC artificial muscles that significantly reduces their power consumption. We discuss some underlying principles of the ion-conducting polymers and show that our method is consistent with theoretical findings. This method is then experimentally tested and verified to the existing methods. The results confirm that energy consumptions of the muscles can be reduced 3.7 times and peak current consumption up to 2.6 times
{"title":"An engineering approach to reduced power consumption of IPMC (ion-polymer metal composite) actuators","authors":"A. Punning, M. Anton, M. Kruusmaa, A. Aabloo","doi":"10.1109/ICAR.2005.1507507","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507507","url":null,"abstract":"Ion-polymer metal composites (IPMC) are electroactive polymer (EAP) materials that behave in electric field similar to biological muscles. Among the shortcomings of an emerging technology like IPMC muscles their energy consumption is one of the most serious. This paper represents a novel open-loop control method for IPMC artificial muscles that significantly reduces their power consumption. We discuss some underlying principles of the ion-conducting polymers and show that our method is consistent with theoretical findings. This method is then experimentally tested and verified to the existing methods. The results confirm that energy consumptions of the muscles can be reduced 3.7 times and peak current consumption up to 2.6 times","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"26 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":"123866498","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.2005.1507445
W. Takano, H. Tanie, Y. Nakamura
Mimesis is a hypothesis that human intelligence originated where motion recognition and motion generation interact through imitation. We previously proposed the mathematical model of mimesis using hidden Markov models (HMM) and constructed the proto symbol space from parameters of each HMM. The proto symbol space included only 10 motion patterns. No attention was paid on the relationship between behavior pattern and parts of body. It is common that a human observer pays an attention to the relationship between the parts of body and the behaviors recognizing performer's behavior pattern. In this paper, we discuss key feature extraction from a rich database of behavior patterns based on probabilistic categorization among HMMs. The method is also applied to extract body parts that characterize behavior patterns
{"title":"Key feature extraction for probabilistic categorization of human motion patterns","authors":"W. Takano, H. Tanie, Y. Nakamura","doi":"10.1109/ICAR.2005.1507445","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507445","url":null,"abstract":"Mimesis is a hypothesis that human intelligence originated where motion recognition and motion generation interact through imitation. We previously proposed the mathematical model of mimesis using hidden Markov models (HMM) and constructed the proto symbol space from parameters of each HMM. The proto symbol space included only 10 motion patterns. No attention was paid on the relationship between behavior pattern and parts of body. It is common that a human observer pays an attention to the relationship between the parts of body and the behaviors recognizing performer's behavior pattern. In this paper, we discuss key feature extraction from a rich database of behavior patterns based on probabilistic categorization among HMMs. The method is also applied to extract body parts that characterize behavior patterns","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"33 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":"127369196","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.2005.1507512
Roozbeh Mottaghi, S. Payandeh
An overview of a probabilistic cooperative tracking approach is presented in this paper. First, a new tutorial-like detailed explanation of the condensation algorithm by Isard and Blake, (1998) is described. Then we apply the probabilistic tracker to track an object (easily extendable to multiple objects) according to multiple degrees of freedom of the cameras that are able to pan, tilt and zoom. To increase the robustness of the tracking system we extend the one camera tracking method to multiple camera case and each camera is considered as an agent that can communicate with a central unit or it can act based on its own decision. Each camera will gain a level of reliability during the tracking that is used in probabilistic tracking method to improve the performance
{"title":"An overview of a probabilistic tracker for multiple cooperative tracking agents","authors":"Roozbeh Mottaghi, S. Payandeh","doi":"10.1109/ICAR.2005.1507512","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507512","url":null,"abstract":"An overview of a probabilistic cooperative tracking approach is presented in this paper. First, a new tutorial-like detailed explanation of the condensation algorithm by Isard and Blake, (1998) is described. Then we apply the probabilistic tracker to track an object (easily extendable to multiple objects) according to multiple degrees of freedom of the cameras that are able to pan, tilt and zoom. To increase the robustness of the tracking system we extend the one camera tracking method to multiple camera case and each camera is considered as an agent that can communicate with a central unit or it can act based on its own decision. Each camera will gain a level of reliability during the tracking that is used in probabilistic tracking method to improve the performance","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"9 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":"121664170","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.2005.1507452
F. Ando, Alfredo Weitzenfeld Ridel
The robotic implementation of Rana computatrix uses a geometric algorithm to regain visual input that is "lost" as the result of its orienting behavior. In this paper the Crowley-Arbib saccade model is implemented in order to give this problem a solution with a biological basis. Three approaches are proposed and simulated and one is used in a small four-legged robot
{"title":"Visual input compensation using the Crowley-Arbib saccade model","authors":"F. Ando, Alfredo Weitzenfeld Ridel","doi":"10.1109/ICAR.2005.1507452","DOIUrl":"https://doi.org/10.1109/ICAR.2005.1507452","url":null,"abstract":"The robotic implementation of Rana computatrix uses a geometric algorithm to regain visual input that is \"lost\" as the result of its orienting behavior. In this paper the Crowley-Arbib saccade model is implemented in order to give this problem a solution with a biological basis. Three approaches are proposed and simulated and one is used in a small four-legged robot","PeriodicalId":428475,"journal":{"name":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","volume":"4 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":"116917249","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：