Pub Date : 2010-06-21DOI: 10.1109/AIS.2010.5547035
Y. Geng, J. Sousa
This paper presents a novel hybrid derivative-free extended Kalman filter, which takes advantage of both the linear time propagation of the Kalman filter and nonlinear measurement propagation of the derivative-free extended Kalman filter. The proposed filter is very suitable for the tightly coupled integration navigation system which consists of USBL or GPS with INS. The computation burden is reduced sharply compare to nonlinear estimation method such as the unscented Kalman filter (UKF). Simulations are conducted to illustrate the effectiveness of the proposed Kalman filter. The performance of the novel filter is as good as that of the UKF in integration navigation.
{"title":"Hybrid derivative-free EKF for USBL/INS tightly-coupled integration in AUV","authors":"Y. Geng, J. Sousa","doi":"10.1109/AIS.2010.5547035","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547035","url":null,"abstract":"This paper presents a novel hybrid derivative-free extended Kalman filter, which takes advantage of both the linear time propagation of the Kalman filter and nonlinear measurement propagation of the derivative-free extended Kalman filter. The proposed filter is very suitable for the tightly coupled integration navigation system which consists of USBL or GPS with INS. The computation burden is reduced sharply compare to nonlinear estimation method such as the unscented Kalman filter (UKF). Simulations are conducted to illustrate the effectiveness of the proposed Kalman filter. The performance of the novel filter is as good as that of the UKF in integration navigation.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85940938","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547015
A. Rahati, F. Kabanza
Managing a dialogue between a student and an intelligent tutoring system is a challenging problem for many applications. It has often been argued and demonstrated that adaptive dialogues between a user and a computer can be generated automatically, using automated planning techniques to plan speech acts. To date such plan-based dialogue generation approaches have relied on deterministic planning algorithms. Consequently they can only handle sequential dialogue structures. In this paper we describe a new approach for automatically planning more general tree-like dialogue structures, by using a nondeterministic planner with incomplete knowledge and sensing. Our approach takes into account incomplete information about the user's knowledge by including queries that the computer can ask to the user to gather missing information that is necessary for an effective feedback. We illustrate our system with an application to an intelligent tutoring system for medical diagnosis.
{"title":"Automated planning of tutorial dialogues","authors":"A. Rahati, F. Kabanza","doi":"10.1109/AIS.2010.5547015","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547015","url":null,"abstract":"Managing a dialogue between a student and an intelligent tutoring system is a challenging problem for many applications. It has often been argued and demonstrated that adaptive dialogues between a user and a computer can be generated automatically, using automated planning techniques to plan speech acts. To date such plan-based dialogue generation approaches have relied on deterministic planning algorithms. Consequently they can only handle sequential dialogue structures. In this paper we describe a new approach for automatically planning more general tree-like dialogue structures, by using a nondeterministic planner with incomplete knowledge and sensing. Our approach takes into account incomplete information about the user's knowledge by including queries that the computer can ask to the user to gather missing information that is necessary for an effective feedback. We illustrate our system with an application to an intelligent tutoring system for medical diagnosis.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85170590","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547031
Hassene Bouraoui, A. Khamis, F. Karray
Verbal interaction provides a natural and social-style interaction mode by which robots can communicate with general public who is likely unknowledgeable in robotics. This interaction mechanism is also very important for a broad range of users such as hands/eyes-busy users, motor-impaired users, users with vision impairment and users working in hostile environments. This paper presents a testbed that can be used to study human-robot verbal interaction. The proposed testbed encompasses a Java-based user interfaces and a user-independent automatic speech recognizer with a modified grammar module in the context of human-robot interaction. The performance of the proposed testbed has been evaluated quantitatively using a set of evaluation metrics such as word correct rate, recognition Time and success and false action rates. The conducted experiments show the promising features of the system.
{"title":"A testbed platform for assessing human-robot verbal interaction","authors":"Hassene Bouraoui, A. Khamis, F. Karray","doi":"10.1109/AIS.2010.5547031","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547031","url":null,"abstract":"Verbal interaction provides a natural and social-style interaction mode by which robots can communicate with general public who is likely unknowledgeable in robotics. This interaction mechanism is also very important for a broad range of users such as hands/eyes-busy users, motor-impaired users, users with vision impairment and users working in hostile environments. This paper presents a testbed that can be used to study human-robot verbal interaction. The proposed testbed encompasses a Java-based user interfaces and a user-independent automatic speech recognizer with a modified grammar module in the context of human-robot interaction. The performance of the proposed testbed has been evaluated quantitatively using a set of evaluation metrics such as word correct rate, recognition Time and success and false action rates. The conducted experiments show the promising features of the system.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83612688","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547023
R. Ramadan, S. Abdel-Mageid
In this paper, we explore different sensor deployment problems and how these problems can be solved optimally using the current packing approaches in terms of small-scale problems. In addition, we consider the deployment of either homogenous or heterogeneous sensing devices. The deployment objectives are to maximize the coverage of the monitored field and use the best of the sensing devices characteristics as well as developing a connected deployment scheme. We propose a novel algorithm named Sequential Packing-based Deployment Algorithm (SPDA) for the deployment of heterogeneous sensors in order to maximize the coverage of the monitored field and connectivity of the deployed sensors. The algorithm is inspired from the packing theories in computational geometry where it benefits from many of the observations properties that are captured from the optimal packing solutions. The algorithm efficiency is examined using different case studies.
{"title":"Efficient deployment of connected sensing devices using circle packing algorithms","authors":"R. Ramadan, S. Abdel-Mageid","doi":"10.1109/AIS.2010.5547023","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547023","url":null,"abstract":"In this paper, we explore different sensor deployment problems and how these problems can be solved optimally using the current packing approaches in terms of small-scale problems. In addition, we consider the deployment of either homogenous or heterogeneous sensing devices. The deployment objectives are to maximize the coverage of the monitored field and use the best of the sensing devices characteristics as well as developing a connected deployment scheme. We propose a novel algorithm named Sequential Packing-based Deployment Algorithm (SPDA) for the deployment of heterogeneous sensors in order to maximize the coverage of the monitored field and connectivity of the deployed sensors. The algorithm is inspired from the packing theories in computational geometry where it benefits from many of the observations properties that are captured from the optimal packing solutions. The algorithm efficiency is examined using different case studies.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81965493","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547032
Howard Li, Alexandru Popa, Carl Thibault, M. Trentini, M. Seto
In this study, a novel robot control framework is presented for multiple autonomous underwater vehicles. In this framework, we incorporate sonar sensor data and integrated navigation system position data in a simulation environment, called UNBeatable-Sim, where complex control behaviors can be executed and analyzed. UNBeatable-Sim is developed by the COllaboration Based Robotics and Automation (COBRA) research group at the University of New Brunswick, Canada. Range and pose sensor data are accumulated in an ocean environment constructed using seabed data collected at Bedford Basin, Nova Scotia, Canada by DRDC Atlantic. A seabed map is generated from the real-world data using UNBeatable-Sim. The underwater vehicle and the seabed are simulated and visualized using OpenGL. An external controller implemented using Matlab and Simulink is used to control the robot model. Simulations of multiple underwater vehicles to navigate in the ocean environment to sense and map the seabed are performed using UNBeatable-Sim to assess the system architecture and controller performance.
{"title":"A software framework for multi-agent control of multiple autonomous underwater vehicles for underwater mine counter-measures","authors":"Howard Li, Alexandru Popa, Carl Thibault, M. Trentini, M. Seto","doi":"10.1109/AIS.2010.5547032","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547032","url":null,"abstract":"In this study, a novel robot control framework is presented for multiple autonomous underwater vehicles. In this framework, we incorporate sonar sensor data and integrated navigation system position data in a simulation environment, called UNBeatable-Sim, where complex control behaviors can be executed and analyzed. UNBeatable-Sim is developed by the COllaboration Based Robotics and Automation (COBRA) research group at the University of New Brunswick, Canada. Range and pose sensor data are accumulated in an ocean environment constructed using seabed data collected at Bedford Basin, Nova Scotia, Canada by DRDC Atlantic. A seabed map is generated from the real-world data using UNBeatable-Sim. The underwater vehicle and the seabed are simulated and visualized using OpenGL. An external controller implemented using Matlab and Simulink is used to control the robot model. Simulations of multiple underwater vehicles to navigate in the ocean environment to sense and map the seabed are performed using UNBeatable-Sim to assess the system architecture and controller performance.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78790599","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547028
L. Veselý, P. Zbranek
Permanent magnet synchronous motors are used in many industrial applications because they have several inherent advantages. However, information about the rotor position is necessary even to be able to control drive speed. Conventional speed and position detection uses encoder and resolver. These sensors significantly increase price, weight, and degrade reliability. Therefore many authors publish papers about algorithms for rotor position and speed estimation. One of state estimation possibility is using extended Kalman filter. Conventional algorithms based on EKF are developed using a simple model of permanent magnet synchronous motor, thereby provide bad performance in the low speed range. Extended Kalman filter using an interior permanent magnet synchronous motor model is described in this paper. This model makes possible for EKF to operate in low speeds. Second part of this paper describes an algorithm Model Reference Adaptive system (MRAS).
{"title":"Sensorless control for synchronous motors","authors":"L. Veselý, P. Zbranek","doi":"10.1109/AIS.2010.5547028","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547028","url":null,"abstract":"Permanent magnet synchronous motors are used in many industrial applications because they have several inherent advantages. However, information about the rotor position is necessary even to be able to control drive speed. Conventional speed and position detection uses encoder and resolver. These sensors significantly increase price, weight, and degrade reliability. Therefore many authors publish papers about algorithms for rotor position and speed estimation. One of state estimation possibility is using extended Kalman filter. Conventional algorithms based on EKF are developed using a simple model of permanent magnet synchronous motor, thereby provide bad performance in the low speed range. Extended Kalman filter using an interior permanent magnet synchronous motor model is described in this paper. This model makes possible for EKF to operate in low speeds. Second part of this paper describes an algorithm Model Reference Adaptive system (MRAS).","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86441776","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547014
A. Alamri, Heung-Nam Kim, Abdulmotaleb El Saddik
Computer-based systems for stroke rehabilitation can potentially reduce complexity in rehabilitation processes. One of important issues among the rehabilitation systems is how to continuously evaluate patient's performances from such systems. Without a proper measurement for patient's performance, therapists suffer from accurate decision making in patient treatments. Therefore, the main focus of this paper is to develop a rehabilitation system that can minimize therapist supervision. To this end, we develop augmented reality-based rehabilitation system that can automatically capture patients' performance as well as visually monitor patients' progress. We also propose performance measurements of patients to improve decision making abilities of therapists. By analyzing performance data, we discover useful rules for further enhancement of the patients' treatment plan.
{"title":"A decision model of stroke patient rehabilitation with augmented reality-based games","authors":"A. Alamri, Heung-Nam Kim, Abdulmotaleb El Saddik","doi":"10.1109/AIS.2010.5547014","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547014","url":null,"abstract":"Computer-based systems for stroke rehabilitation can potentially reduce complexity in rehabilitation processes. One of important issues among the rehabilitation systems is how to continuously evaluate patient's performances from such systems. Without a proper measurement for patient's performance, therapists suffer from accurate decision making in patient treatments. Therefore, the main focus of this paper is to develop a rehabilitation system that can minimize therapist supervision. To this end, we develop augmented reality-based rehabilitation system that can automatically capture patients' performance as well as visually monitor patients' progress. We also propose performance measurements of patients to improve decision making abilities of therapists. By analyzing performance data, we discover useful rules for further enhancement of the patients' treatment plan.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82646775","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547025
M. Al-Mulla, F. Sepulveda
Surface Electromyography (sEMG) activity of the biceps muscle was recorded from nine subjects. Data were recorded while subjects performed dynamic contraction until fatigue. The signals were initially segmented into two parts (Non-Fatigue and Transition-to-Fatigue) to enable the evolutionary process. A novel feature was evolved by selecting then using a combination of the eleven sEMG muscle fatigue features and six mathematical operators. The evolutionary program used the DB index in its fitness function to derive the best feature that best separate the two segments (Non-Fatigue and Transition-to-Fatigue), for both Maximum Dynamic Strength (MDS) percentage of 40 and 70 MDS. Using the evolved feature we enabled an ANN to predict the time to fatigue by using only twenty percent of the total sEMG signal with an average prediction error of 9.22%.
{"title":"Predicting the time to localized muscle fatigue using ANN and evolved sEMG feature","authors":"M. Al-Mulla, F. Sepulveda","doi":"10.1109/AIS.2010.5547025","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547025","url":null,"abstract":"Surface Electromyography (sEMG) activity of the biceps muscle was recorded from nine subjects. Data were recorded while subjects performed dynamic contraction until fatigue. The signals were initially segmented into two parts (Non-Fatigue and Transition-to-Fatigue) to enable the evolutionary process. A novel feature was evolved by selecting then using a combination of the eleven sEMG muscle fatigue features and six mathematical operators. The evolutionary program used the DB index in its fitness function to derive the best feature that best separate the two segments (Non-Fatigue and Transition-to-Fatigue), for both Maximum Dynamic Strength (MDS) percentage of 40 and 70 MDS. Using the evolved feature we enabled an ANN to predict the time to fatigue by using only twenty percent of the total sEMG signal with an average prediction error of 9.22%.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89787084","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547037
Robert Collier, M. Wineberg
The construction of an adaptive landscape visualization entails the representation of the higher dimensional chromosome space onto a two-dimensional plane from which a depiction of the landscape can be created. Although it can sometimes be difficult to justify the investment of computational expense necessary to perform this representation properly, Van Wijk's visualization model is ideally suited for use as a framework in which to compare different adaptive landscape visualizations. This model is used to demonstrate that an adaptive landscape visualization that is constructed with an established multidimensional scaling technique will result in a visualization that imparts more accurate insights, and is thus more valuable, than one that does not first attempt a multidimensional scaling of the chromosome space.
{"title":"Evaluating approaches to adaptive landscape visualization construction","authors":"Robert Collier, M. Wineberg","doi":"10.1109/AIS.2010.5547037","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547037","url":null,"abstract":"The construction of an adaptive landscape visualization entails the representation of the higher dimensional chromosome space onto a two-dimensional plane from which a depiction of the landscape can be created. Although it can sometimes be difficult to justify the investment of computational expense necessary to perform this representation properly, Van Wijk's visualization model is ideally suited for use as a framework in which to compare different adaptive landscape visualizations. This model is used to demonstrate that an adaptive landscape visualization that is constructed with an established multidimensional scaling technique will result in a visualization that imparts more accurate insights, and is thus more valuable, than one that does not first attempt a multidimensional scaling of the chromosome space.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82071879","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 : 2010-06-21DOI: 10.1109/AIS.2010.5547022
E. Pereira, J. Sousa
We discuss the problem of dynamic reallocation of vehicles among teams of Unmanned Air Vehicles (UAV) executing concurrently. Each team addresses a task that consists of a sequence of subtasks to be executed in an adversary environment, where the vehicles face the risk of becoming inoperative. Our approach consists on separating the problem into a planning procedure followed by an optimal control problem, which is solved using stochastic dynamic programming (DP). We consider mixed-initiative interactions, where human operators are able to tune parameters of the problem according to their experience. The main goal of execution control is to balance the performance of teams in order to increase the success of the overall mission.
{"title":"Reallocations in teams of UAVs using dynamic programming and mixed initiative interactions","authors":"E. Pereira, J. Sousa","doi":"10.1109/AIS.2010.5547022","DOIUrl":"https://doi.org/10.1109/AIS.2010.5547022","url":null,"abstract":"We discuss the problem of dynamic reallocation of vehicles among teams of Unmanned Air Vehicles (UAV) executing concurrently. Each team addresses a task that consists of a sequence of subtasks to be executed in an adversary environment, where the vehicles face the risk of becoming inoperative. Our approach consists on separating the problem into a planning procedure followed by an optimal control problem, which is solved using stochastic dynamic programming (DP). We consider mixed-initiative interactions, where human operators are able to tune parameters of the problem according to their experience. The main goal of execution control is to balance the performance of teams in order to increase the success of the overall mission.","PeriodicalId":71187,"journal":{"name":"自主智能系统(英文)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2010-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79774230","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：