Pub Date : 2007-12-01DOI: 10.1109/ARSO.2007.4531418
S. Stan, V. Maties, R. Balan
In this paper a mono-objective optimum design procedure for parallel robot is outlined by using optimality criterion of workspace and numerical aspects. A mono- objective optimization problem is formulated by referring to a basic performance of parallel robots. Additional objective functions can be used to extend the proposed design procedure to more general but specific design problems. A kinematic optimization was performed to maximize the workspace of the mini parallel robot. Optimization was performed using genetic algorithms and simulated annealing optimization methods.
{"title":"Optimization of workspace of a 2 DOF parallel minirobot using Genetic Algorithms and Simulated Annealing optimization methods","authors":"S. Stan, V. Maties, R. Balan","doi":"10.1109/ARSO.2007.4531418","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531418","url":null,"abstract":"In this paper a mono-objective optimum design procedure for parallel robot is outlined by using optimality criterion of workspace and numerical aspects. A mono- objective optimization problem is formulated by referring to a basic performance of parallel robots. Additional objective functions can be used to extend the proposed design procedure to more general but specific design problems. A kinematic optimization was performed to maximize the workspace of the mini parallel robot. Optimization was performed using genetic algorithms and simulated annealing optimization methods.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122465937","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531421
Jung-Wei Hong, K. Song
Extracting facial feature is a key step in facial expression recognition (FER). Inaccurate feature extraction very often results in erroneous categorizing of facial expressions. Especially in robotic application, environmental factors such as illumination variation may cause FER system to extract feature inaccurately. In this paper, we propose a robust facial feature point extraction method to recognize facial expression in various lighting conditions. Before extracting facial features, a face is localized and segmented from a digitized image frame. Face preprocessing stage consists of face normalization and feature region localization steps to extract facial features efficiently. As regions of interest corresponding to relevant features are determined, Gabor jets are applied based on Gabor wavelet transformation to extract the facial points. Gabor jets are more invariable and reliable than gray-level values, which suffer from ambiguity as well as illumination variation while representing local features. Each feature point can be matched by a phase-sensitivity similarity function in the relevant regions of interest. Finally, the feature values are evaluated from the geometric displacement of facial points. After tested using the AR face database and the database built in our lab, average facial expression recognition rates of 84.1% and 81.3% are obtained respectively.
{"title":"Facial expression recognition under illumination variation","authors":"Jung-Wei Hong, K. Song","doi":"10.1109/ARSO.2007.4531421","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531421","url":null,"abstract":"Extracting facial feature is a key step in facial expression recognition (FER). Inaccurate feature extraction very often results in erroneous categorizing of facial expressions. Especially in robotic application, environmental factors such as illumination variation may cause FER system to extract feature inaccurately. In this paper, we propose a robust facial feature point extraction method to recognize facial expression in various lighting conditions. Before extracting facial features, a face is localized and segmented from a digitized image frame. Face preprocessing stage consists of face normalization and feature region localization steps to extract facial features efficiently. As regions of interest corresponding to relevant features are determined, Gabor jets are applied based on Gabor wavelet transformation to extract the facial points. Gabor jets are more invariable and reliable than gray-level values, which suffer from ambiguity as well as illumination variation while representing local features. Each feature point can be matched by a phase-sensitivity similarity function in the relevant regions of interest. Finally, the feature values are evaluated from the geometric displacement of facial points. After tested using the AR face database and the database built in our lab, average facial expression recognition rates of 84.1% and 81.3% are obtained respectively.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126177697","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531425
T.-H.S. Li, Chih-Yang Chen, Ying-Chieh Yeh, C. Yang, Hong-Kai Huang, H. Hung, C. Chu, Shiuan-Hung Hsu, Ding-Yao Huang, Bing-Rung Tsai, Min-Chi Gau, Ren-Jau Jang
The motivation of this paper is to set up a surveillance and security robot team (SSRT, three autonomous mobile robots and a surveillance and security control (SSC) center. The SSC center communicates with clients via the Internet which can assign patrol scheduler for each robot. The SSRT shares the environmental information among team members through a wireless communication network. The architecture of the SSRT can be divided into two parts. The first one is sensory feedback park. Each surveillance and security robot (SSR) can transmit and receive useful some data, for example, the electric energy residue and the result of patrol, to SSC center via the internet. The other one is mission assignment. The SSC center sorts out the priority of each SSR for the mission execution and assigns each SSR a suitable mission, for example, if any unusual event happens, the SSR will alarm and send the pictures to the SSC center, and then the center will announce the robot employer and assign the optimal patrol role for every robot. The most suitable robot will go to support the incident area, while the other robots will evacuate people to decrease any possible damage. A fuzzy logic decision algorithm is adopted to find the optimal path for each robot to reach the incident location. By combining RFID data with the vision system to recognize the bar-code characteristics in the environment, the self-localization and the patrol routine for each robot can be accomplished. Each robot possesses the auto-recharge function which can recharge itself automatically. Finally, real-time experiments are executed to demonstrate the feasibility and effectiveness of the proposed schemes.
{"title":"An autonomous surveillance and security robot team","authors":"T.-H.S. Li, Chih-Yang Chen, Ying-Chieh Yeh, C. Yang, Hong-Kai Huang, H. Hung, C. Chu, Shiuan-Hung Hsu, Ding-Yao Huang, Bing-Rung Tsai, Min-Chi Gau, Ren-Jau Jang","doi":"10.1109/ARSO.2007.4531425","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531425","url":null,"abstract":"The motivation of this paper is to set up a surveillance and security robot team (SSRT, three autonomous mobile robots and a surveillance and security control (SSC) center. The SSC center communicates with clients via the Internet which can assign patrol scheduler for each robot. The SSRT shares the environmental information among team members through a wireless communication network. The architecture of the SSRT can be divided into two parts. The first one is sensory feedback park. Each surveillance and security robot (SSR) can transmit and receive useful some data, for example, the electric energy residue and the result of patrol, to SSC center via the internet. The other one is mission assignment. The SSC center sorts out the priority of each SSR for the mission execution and assigns each SSR a suitable mission, for example, if any unusual event happens, the SSR will alarm and send the pictures to the SSC center, and then the center will announce the robot employer and assign the optimal patrol role for every robot. The most suitable robot will go to support the incident area, while the other robots will evacuate people to decrease any possible damage. A fuzzy logic decision algorithm is adopted to find the optimal path for each robot to reach the incident location. By combining RFID data with the vision system to recognize the bar-code characteristics in the environment, the self-localization and the patrol routine for each robot can be accomplished. Each robot possesses the auto-recharge function which can recharge itself automatically. Finally, real-time experiments are executed to demonstrate the feasibility and effectiveness of the proposed schemes.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129638019","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531424
K. Su, J. Tzou, C. Liu
Based on the measurements of multiple sensors, this paper presents a residual power detection system for a mobile robot. We use four current sensors to measure the current variety of the mobile robot, and use multilevel multisensor fusion method to detect and diagnosis current sensor and voltage signals status. Moreover, a two level method is used to isolate faulty measured value such that more exact current status to be obtained. In this method, a redundant management method and a statistical prediction method are used in levels one and two, respectively. We use the same method to measure voltage of power system for mobile robots, and isolate faulty measured values. We design the power detection and isolation module using HOLTEK microchip according to the redundant management method. This module can transmit measured value and decision output to main controller (IPC) using series interface (RS232). However, it is possible that this method is faulty. In this case, the IPC can decide an exact power measured value according the statistical signal prediction method. Then we can predict the residual power of mobile robots using polynomial regression algorithm. Finally, we implement the proposed method on the experiment scenario of can set a power threshold value to calculate the critical time for the mobile robot. Meanwhile, experimental results are given to show the feasibility of the proposed method.
{"title":"Development of a multisensor-based residual power prediction system for mobile robots","authors":"K. Su, J. Tzou, C. Liu","doi":"10.1109/ARSO.2007.4531424","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531424","url":null,"abstract":"Based on the measurements of multiple sensors, this paper presents a residual power detection system for a mobile robot. We use four current sensors to measure the current variety of the mobile robot, and use multilevel multisensor fusion method to detect and diagnosis current sensor and voltage signals status. Moreover, a two level method is used to isolate faulty measured value such that more exact current status to be obtained. In this method, a redundant management method and a statistical prediction method are used in levels one and two, respectively. We use the same method to measure voltage of power system for mobile robots, and isolate faulty measured values. We design the power detection and isolation module using HOLTEK microchip according to the redundant management method. This module can transmit measured value and decision output to main controller (IPC) using series interface (RS232). However, it is possible that this method is faulty. In this case, the IPC can decide an exact power measured value according the statistical signal prediction method. Then we can predict the residual power of mobile robots using polynomial regression algorithm. Finally, we implement the proposed method on the experiment scenario of can set a power threshold value to calculate the critical time for the mobile robot. Meanwhile, experimental results are given to show the feasibility of the proposed method.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126512084","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531432
Yangmin Li, Qingsong Xu
A new three degrees of freedom (3-DOF) translational parallel manipulator (TPM) constructed only with prismatic (P), cylindrical (C), revolute (R) joints has been proposed in this paper. The mobility of the 3-PCR TPM is analyzed via screw theory. Afterwards, the inverse kinematics, forward kinematics, and velocity analysis are performed and the singularity problems are investigated. In addition, the reachable workspace has been determined analytically and compared with and without consideration of mechanical constraints. It is shown that the 3-PCR TPM owns a smaller size output platform than the existing 3-PRC one, and then has more wide applications. In view of applications, the 3-PCR TPM is adopted as a CPR (cardiopulmonary resuscitation) medical robot, and another new 3-PCR TPM with an orthogonal architecture is presented and its application in micro/nano scale manipulation has been exhibited through the employment into an automatic biological cell injection system. The results presented in the paper are helpful for the design and development of several new TPMs for various applications.
{"title":"Design and application of a new 3-DOF translational parallel manipulator","authors":"Yangmin Li, Qingsong Xu","doi":"10.1109/ARSO.2007.4531432","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531432","url":null,"abstract":"A new three degrees of freedom (3-DOF) translational parallel manipulator (TPM) constructed only with prismatic (P), cylindrical (C), revolute (R) joints has been proposed in this paper. The mobility of the 3-PCR TPM is analyzed via screw theory. Afterwards, the inverse kinematics, forward kinematics, and velocity analysis are performed and the singularity problems are investigated. In addition, the reachable workspace has been determined analytically and compared with and without consideration of mechanical constraints. It is shown that the 3-PCR TPM owns a smaller size output platform than the existing 3-PRC one, and then has more wide applications. In view of applications, the 3-PCR TPM is adopted as a CPR (cardiopulmonary resuscitation) medical robot, and another new 3-PCR TPM with an orthogonal architecture is presented and its application in micro/nano scale manipulation has been exhibited through the employment into an automatic biological cell injection system. The results presented in the paper are helpful for the design and development of several new TPMs for various applications.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115630682","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531411
Shih-Wei Peng, Feng‐Li Lian
This paper presents a novel design of a multi-functional bed for the bedridden patients, including elderly and maim persons. Most patients encounter difficulty in posture changing and moving. To overcome these problems, the proposed design conception is validated through the consolation with medical staff as well as from literature survey. A belt system is designed for transferring patient from the bed to a wheelchair. The bed mechanism design is analyzed first by the detailed mathematical model and related design parameters and functionalities are verified by the computer aided design software: Solid Works. Finally, simulation results demonstrate the effectiveness of the proposed design approach for solving these two problems.
{"title":"Design of multi-functional bed for bedridden patient","authors":"Shih-Wei Peng, Feng‐Li Lian","doi":"10.1109/ARSO.2007.4531411","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531411","url":null,"abstract":"This paper presents a novel design of a multi-functional bed for the bedridden patients, including elderly and maim persons. Most patients encounter difficulty in posture changing and moving. To overcome these problems, the proposed design conception is validated through the consolation with medical staff as well as from literature survey. A belt system is designed for transferring patient from the bed to a wheelchair. The bed mechanism design is analyzed first by the detailed mathematical model and related design parameters and functionalities are verified by the computer aided design software: Solid Works. Finally, simulation results demonstrate the effectiveness of the proposed design approach for solving these two problems.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122045797","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531414
R. Luo, Sung-Sheng Huang, Wei-Lung Hsu
A common design of the sensor node is usually not in mobility. The major reason is that long-term motion will cost a lot of energy. But from the other point of view, a mobile sensor node is useful. The accuracy of localization plays an important role for a mobile sensor node. However it is very hard to achieve much highly precise localization for getting a mobile sensor node position data. How to enhance the performance of localization is the most common and important goals. In this paper we used CI (covariance intersection) theory to fuse RSS (received signal strength) and dead-reckoning localization in order to increase the accuracy of localization. Our experiment result shows that the mean distance error is below four percentages. Comparing to RSS and dead-reckoning localization, the accuracy of localization is improved. This paper brings out a reliable algorithm through CI data fusion method to fuse the RSS and dead-reckoning localization estimations.
{"title":"Mobile sensor node localization based on sensor fusion using covariance intersection approach","authors":"R. Luo, Sung-Sheng Huang, Wei-Lung Hsu","doi":"10.1109/ARSO.2007.4531414","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531414","url":null,"abstract":"A common design of the sensor node is usually not in mobility. The major reason is that long-term motion will cost a lot of energy. But from the other point of view, a mobile sensor node is useful. The accuracy of localization plays an important role for a mobile sensor node. However it is very hard to achieve much highly precise localization for getting a mobile sensor node position data. How to enhance the performance of localization is the most common and important goals. In this paper we used CI (covariance intersection) theory to fuse RSS (received signal strength) and dead-reckoning localization in order to increase the accuracy of localization. Our experiment result shows that the mean distance error is below four percentages. Comparing to RSS and dead-reckoning localization, the accuracy of localization is improved. This paper brings out a reliable algorithm through CI data fusion method to fuse the RSS and dead-reckoning localization estimations.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114801805","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531429
C. H. Chiang, Po Jui Chiang, J.C.-C. Fei, J. Liu
Theoretically both of fast marching method (FMM) and A* SEARCH have the same time complexity of O(N log N) , where N is the number of grid points in a map, and guarantee to find an optimal solution if this path exists. This paper examines the effect of alteration of resolution of map on the performance of path planning by A* and FMM on 2D rectangular grid environments. Our observations on the basis of comparative simulations in three test environments at different resolutions are that: A* is more focused and thus faster to generate a polygonal line (continuous but not smooth) path, while FMM generates a better curvature-control, generally smoother and shorter path that is a numerically consistent approximation to the true shortest continuous path as the resolution of map is finer and finer. The difference of path quality for these two methods is more significant as the resolution is finer.
{"title":"A comparative study of implementing Fast Marching Method and A* SEARCH for mobile robot path planning in grid environment: Effect of map resolution","authors":"C. H. Chiang, Po Jui Chiang, J.C.-C. Fei, J. Liu","doi":"10.1109/ARSO.2007.4531429","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531429","url":null,"abstract":"Theoretically both of fast marching method (FMM) and A* SEARCH have the same time complexity of O(N log N) , where N is the number of grid points in a map, and guarantee to find an optimal solution if this path exists. This paper examines the effect of alteration of resolution of map on the performance of path planning by A* and FMM on 2D rectangular grid environments. Our observations on the basis of comparative simulations in three test environments at different resolutions are that: A* is more focused and thus faster to generate a polygonal line (continuous but not smooth) path, while FMM generates a better curvature-control, generally smoother and shorter path that is a numerically consistent approximation to the true shortest continuous path as the resolution of map is finer and finer. The difference of path quality for these two methods is more significant as the resolution is finer.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"326 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122733068","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 : 2007-12-01DOI: 10.1109/ARSO.2007.4531415
R. Luo, Chun C. Lai
This paper presents a probability fusion methodology with a decision rule for a feature extraction of indoor environment. Two range sensors with complementary property are equipped on a mobile service robot. One is a servo sonar ring composed by Polaroid 6500 ultrasonic rangers and the other is a Hokuyo infrared range-finder. For a real indoor environment is usually composed of different objects with variant material characteristics such as sound absorbed or light refraction. Theses may cause the sensor measurement failure to imperil the localization estimation procedure of an indoor service robot. Thus, multi-sensor fusion with a decision methodology is necessary for feasibility and reliability while service mobile robot is working in a compound indoor environment.
{"title":"Indoor mobile robot localization using probabilistic multi-sensor fusion","authors":"R. Luo, Chun C. Lai","doi":"10.1109/ARSO.2007.4531415","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531415","url":null,"abstract":"This paper presents a probability fusion methodology with a decision rule for a feature extraction of indoor environment. Two range sensors with complementary property are equipped on a mobile service robot. One is a servo sonar ring composed by Polaroid 6500 ultrasonic rangers and the other is a Hokuyo infrared range-finder. For a real indoor environment is usually composed of different objects with variant material characteristics such as sound absorbed or light refraction. Theses may cause the sensor measurement failure to imperil the localization estimation procedure of an indoor service robot. Thus, multi-sensor fusion with a decision methodology is necessary for feasibility and reliability while service mobile robot is working in a compound indoor environment.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128028527","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}
This paper presents methodologies and techniques for multi-sensory fuzzy hybrid navigation of an active mobile robot assistant for the elderly people in known, cluttered and dynamic indoor environments. For self-localization, the geometric and topological representations are combined together to maintain the advantages of them and counteract their disadvantages. By using RFID system, the estimation of position hypothesis for similar regions in a known environment can be reduced. The global optimal path composed of via points is determined by using Dijkstra's dynamic programming approach. Fuzzy adaptive speed control law is designed to make the robot adapt to various users' speeds. Safe fuzzy hybrid navigation is achieved by fusing adaptive speed, goal-seeking and obstacle- avoidance from the sensing data of laser scanner and ultrasonic rangers. In addition, Experimental results are conducted to show the effectiveness and merits of the proposed methods.
{"title":"Fuzzy hybrid navigation of an active mobile robotic assistant: A multisensory fusion approach","authors":"Ching-Chih Tsai, Ssu-Min Hu, Hsu-Chih Huang, Shih-Min Hsieh","doi":"10.1109/ARSO.2007.4531423","DOIUrl":"https://doi.org/10.1109/ARSO.2007.4531423","url":null,"abstract":"This paper presents methodologies and techniques for multi-sensory fuzzy hybrid navigation of an active mobile robot assistant for the elderly people in known, cluttered and dynamic indoor environments. For self-localization, the geometric and topological representations are combined together to maintain the advantages of them and counteract their disadvantages. By using RFID system, the estimation of position hypothesis for similar regions in a known environment can be reduced. The global optimal path composed of via points is determined by using Dijkstra's dynamic programming approach. Fuzzy adaptive speed control law is designed to make the robot adapt to various users' speeds. Safe fuzzy hybrid navigation is achieved by fusing adaptive speed, goal-seeking and obstacle- avoidance from the sensing data of laser scanner and ultrasonic rangers. In addition, Experimental results are conducted to show the effectiveness and merits of the proposed methods.","PeriodicalId":344670,"journal":{"name":"2007 IEEE Workshop on Advanced Robotics and Its Social Impacts","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132472487","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：