Pub Date : 2013-12-02DOI: 10.1109/URAI.2013.6677388
Kap-Ho Seo, Yongsik Park, Sungjo Yun, Sung-Ho Park, Jungsoo Jun, Kwang-Woo Jeon
Robotic gait rehabilitation devices enable efficient and convenient gait rehabilitation by mimicking the functions of physical theraphists. In manual gait rehabilitation training, physical theraphists have patients practice and memorize normal gait patterns by applying assistive torque to the patient's joint once the patient's gait deviates from the normal gait. Thus, one of the most important factors in robotic gait rehabilitation devices is to determine the assistive torque to the patient's joint during rehabilitation training. In order to calculate the assistive torque, the desired gait trajectory for affected leg should be determined. This reference trajectory is obtained from his healthy leg. The obtained signal has many noisy factors. Therefore, after conditioning the signal, the suitable pattern is applied to the developed system. This procedure is called “gait pattern generation” in this paper. It is described and discussed in detail.
{"title":"Gait pattern generation for gait rehabilitation","authors":"Kap-Ho Seo, Yongsik Park, Sungjo Yun, Sung-Ho Park, Jungsoo Jun, Kwang-Woo Jeon","doi":"10.1109/URAI.2013.6677388","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677388","url":null,"abstract":"Robotic gait rehabilitation devices enable efficient and convenient gait rehabilitation by mimicking the functions of physical theraphists. In manual gait rehabilitation training, physical theraphists have patients practice and memorize normal gait patterns by applying assistive torque to the patient's joint once the patient's gait deviates from the normal gait. Thus, one of the most important factors in robotic gait rehabilitation devices is to determine the assistive torque to the patient's joint during rehabilitation training. In order to calculate the assistive torque, the desired gait trajectory for affected leg should be determined. This reference trajectory is obtained from his healthy leg. The obtained signal has many noisy factors. Therefore, after conditioning the signal, the suitable pattern is applied to the developed system. This procedure is called “gait pattern generation” in this paper. It is described and discussed in detail.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115838322","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677394
Rui-Jun Yan, Jing Wu, Ji Yeong Lee
This paper proposes the occlusion avoidance method in comers-based simultaneous localization and mapping (SLAM) with different data association algorithms. The redundant or wrong features are extracted if part of the object is occluded. The comers are chosen by intersecting two adjacent line segments and selecting the end-points of some special line segment. When two segments are far enough, the nearest two end-points of these two lines are considered as candidate comers. Then one of two candidates is stored as final comer with shorter distance of laser beam. However, if the line segment with this corner is very short, this comer is ignored because it may be just part of the object with complex surface, such as column. After extracting theses comers, they have been used in estimating the state of mobile robot and previous landmarks. To have a better matching result, two data association algorithms are applied in constructing the correspondence between new features and stored map features. The experiment result in indoor environment shows the validity of proposed method.
{"title":"Occlusion avoidance in corners-based SLAM with different data association algorithms","authors":"Rui-Jun Yan, Jing Wu, Ji Yeong Lee","doi":"10.1109/URAI.2013.6677394","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677394","url":null,"abstract":"This paper proposes the occlusion avoidance method in comers-based simultaneous localization and mapping (SLAM) with different data association algorithms. The redundant or wrong features are extracted if part of the object is occluded. The comers are chosen by intersecting two adjacent line segments and selecting the end-points of some special line segment. When two segments are far enough, the nearest two end-points of these two lines are considered as candidate comers. Then one of two candidates is stored as final comer with shorter distance of laser beam. However, if the line segment with this corner is very short, this comer is ignored because it may be just part of the object with complex surface, such as column. After extracting theses comers, they have been used in estimating the state of mobile robot and previous landmarks. To have a better matching result, two data association algorithms are applied in constructing the correspondence between new features and stored map features. The experiment result in indoor environment shows the validity of proposed method.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115089955","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677402
Alchan Yoon, J. Kwon, F. Park
We propose a loop closure detection technique for a monocular SLAM system proposed in [1], which uses planar landmarks to describe 3-D environments. In [1], the camera state and the landmark plane normal is represented as SE(3) and SO(3), respectively, which are both Lie group. Loop closing techniques for feature map which consist of Lie group elements should consider the geometrical properties of Lie group.
{"title":"A loop closure technique for monocular SLAM with locally planar landmarks","authors":"Alchan Yoon, J. Kwon, F. Park","doi":"10.1109/URAI.2013.6677402","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677402","url":null,"abstract":"We propose a loop closure detection technique for a monocular SLAM system proposed in [1], which uses planar landmarks to describe 3-D environments. In [1], the camera state and the landmark plane normal is represented as SE(3) and SO(3), respectively, which are both Lie group. Loop closing techniques for feature map which consist of Lie group elements should consider the geometrical properties of Lie group.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116270699","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677379
Eun-Cheol Shin, J. Ryu, Hogil Lee
In a tele-operation system, the work efficiency can be improved by altering the impedance of a slave robot in accordance with the characteristics of the work. The impedance intended by an operator should be measured because the impedance of a slave robot should reflect the intention of the operator. Besides, the measured impedance should be obliged to include the information of its value and direction. In this paper, the method of using a single-axis force sensor as well as the posture of an operator is proposed so as to measure the value and direction of the impedance intended by the operator. Also, the proposed method is applied to Phantom that is widely used in tele-operation systems to validate its usefulness.
{"title":"Measurement of human arm impedance using the human arm posture","authors":"Eun-Cheol Shin, J. Ryu, Hogil Lee","doi":"10.1109/URAI.2013.6677379","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677379","url":null,"abstract":"In a tele-operation system, the work efficiency can be improved by altering the impedance of a slave robot in accordance with the characteristics of the work. The impedance intended by an operator should be measured because the impedance of a slave robot should reflect the intention of the operator. Besides, the measured impedance should be obliged to include the information of its value and direction. In this paper, the method of using a single-axis force sensor as well as the posture of an operator is proposed so as to measure the value and direction of the impedance intended by the operator. Also, the proposed method is applied to Phantom that is widely used in tele-operation systems to validate its usefulness.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128588832","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677398
Jae-Y. Lee, Wonpil Yu
One of the main problems relating RANSAC estimation is to determine the inlier threshold adaptively depending on the variance of inliers. In this paper, we propose a novel method that estimates the inlier threshold adaptively from the observations, giving a threshold-free RANSAC. A minimum assumption of our method is that the lower bound of inlier ratio is known in advance and the variance of inliers follows Gaussian. We also describe a simple motion flow tracker as an application of the proposed method. In the experiment we show the effectiveness of the proposed method by comparing tracking performance with and without adaptive estimation of inlier threshold.
{"title":"Adaptive estimation of inlier and outlier threshold","authors":"Jae-Y. Lee, Wonpil Yu","doi":"10.1109/URAI.2013.6677398","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677398","url":null,"abstract":"One of the main problems relating RANSAC estimation is to determine the inlier threshold adaptively depending on the variance of inliers. In this paper, we propose a novel method that estimates the inlier threshold adaptively from the observations, giving a threshold-free RANSAC. A minimum assumption of our method is that the lower bound of inlier ratio is known in advance and the variance of inliers follows Gaussian. We also describe a simple motion flow tracker as an application of the proposed method. In the experiment we show the effectiveness of the proposed method by comparing tracking performance with and without adaptive estimation of inlier threshold.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127503555","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677378
Joomin Kim, Sungsik Yun, Joovounz Yoo, Daewon Kim
In this paper, the implementation of a work distribution function for tele-operation under multi-user and multi-robot environments is described. First of all, XML-based UDS(Unit-task Description Structure) is defined to make task scenarios, to distribute the work to multi-users and to consider emergency states in the task. Considering the role of users and control methods, various kinds of switching modes are defined, and a switching controller is designed. To prove the work distribution function, a simulation environment including a Marilou robotic simulator based slave robot environment is implemented. In this environment, the effectiveness of the work distribution function is tested.
{"title":"Implementation of N:1/1:N work distribution function for tele-operation under multi-user and multi-robot environments","authors":"Joomin Kim, Sungsik Yun, Joovounz Yoo, Daewon Kim","doi":"10.1109/URAI.2013.6677378","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677378","url":null,"abstract":"In this paper, the implementation of a work distribution function for tele-operation under multi-user and multi-robot environments is described. First of all, XML-based UDS(Unit-task Description Structure) is defined to make task scenarios, to distribute the work to multi-users and to consider emergency states in the task. Considering the role of users and control methods, various kinds of switching modes are defined, and a switching controller is designed. To prove the work distribution function, a simulation environment including a Marilou robotic simulator based slave robot environment is implemented. In this environment, the effectiveness of the work distribution function is tested.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130090529","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677405
Kyungdon Joo, Tae-Hyun Oh, In-So Kweon
Recently, the sparsity model has been applied to photometric stereo by modeling non-Lambertian artifacts as sparse components. As one of these efforts, we present l1-based photometric stereo for the non-Lambertian corruptions. A solution method was derived using the Augmented Lagrange Multiplier (ALM) method, which effectively solves the constrained problem by solving the sub-problems for surface normal and sparse corruptions iteratively. Experiments demonstrate the applicability of our method by comparing with the Least Square method and the l1 baseline method.
{"title":"L1-based photometric stereo via augmented lagrange multiplier method","authors":"Kyungdon Joo, Tae-Hyun Oh, In-So Kweon","doi":"10.1109/URAI.2013.6677405","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677405","url":null,"abstract":"Recently, the sparsity model has been applied to photometric stereo by modeling non-Lambertian artifacts as sparse components. As one of these efforts, we present l1-based photometric stereo for the non-Lambertian corruptions. A solution method was derived using the Augmented Lagrange Multiplier (ALM) method, which effectively solves the constrained problem by solving the sub-problems for surface normal and sparse corruptions iteratively. Experiments demonstrate the applicability of our method by comparing with the Least Square method and the l1 baseline method.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130582336","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677421
J. Kim, B. Kim
The time-optimal straight-line trajectory planning problem on hill (TO-STH) is solved for two-wheeled mobile robots (TMRs). Our studies are based on the dynamics of mobile robots with actuator motors on hill. After formulating the dynamics, the TO-STH solution should be obtained satisfying initial/final postures/velocities, straight-line road on hill, and bounded motor control inputs. Then we developed TO-STH algorithm by phase-plane techniques with optimality condition. Finally, verification of the proposed algorithm is shown via extensive simulations.
{"title":"Time-optimal straight-line trajectory planning on hill for two-wheeled mobile robots","authors":"J. Kim, B. Kim","doi":"10.1109/URAI.2013.6677421","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677421","url":null,"abstract":"The time-optimal straight-line trajectory planning problem on hill (TO-STH) is solved for two-wheeled mobile robots (TMRs). Our studies are based on the dynamics of mobile robots with actuator motors on hill. After formulating the dynamics, the TO-STH solution should be obtained satisfying initial/final postures/velocities, straight-line road on hill, and bounded motor control inputs. Then we developed TO-STH algorithm by phase-plane techniques with optimality condition. Finally, verification of the proposed algorithm is shown via extensive simulations.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129246708","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677292
K. Wada, Takayoshi Tanaka, Yusuke Suganuma, Mime Hashimoto, Toshihiko Suzuki
Recently, public housing are rebuilt for the elderly in the center of a city. The main purposes of rebuilding are flatting floors, installation of handrails, and expansion of bathroom and toilet for people using wheelchair. Because giving priority to them, spaces for kitchen and dining room are very limited. The kitchen doesn't have enough cooking and storage space; and dining room doesn't have space for dining table. In this study, we propose a robot module that can expand spaces for cooking, store electric appliances, cooking tools and tableware, and transform into the dining table.
{"title":"Kitchen extension robot module for elderly housing","authors":"K. Wada, Takayoshi Tanaka, Yusuke Suganuma, Mime Hashimoto, Toshihiko Suzuki","doi":"10.1109/URAI.2013.6677292","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677292","url":null,"abstract":"Recently, public housing are rebuilt for the elderly in the center of a city. The main purposes of rebuilding are flatting floors, installation of handrails, and expansion of bathroom and toilet for people using wheelchair. Because giving priority to them, spaces for kitchen and dining room are very limited. The kitchen doesn't have enough cooking and storage space; and dining room doesn't have space for dining table. In this study, we propose a robot module that can expand spaces for cooking, store electric appliances, cooking tools and tableware, and transform into the dining table.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123194673","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 : 2013-12-02DOI: 10.1109/URAI.2013.6677446
Jongmin Yoon, Jongju Shin, Daijin Kim
This paper presents a method which can detect multi-pose faces for robot. To overcome a disadvantage of conventional single-view face detection. we compute hyperplane using Linear Discriminant Analysis (LDA). These hyperplane are used to separate two different classes finely. This method could reduce false positive rate on branching nodes significantly, as well as the number of unnecessary branches. Consequently, overall speed of the detector could be improved about 24 percent compared to the case without hyperplane partition.
{"title":"Multi-pose face detection for silver robots","authors":"Jongmin Yoon, Jongju Shin, Daijin Kim","doi":"10.1109/URAI.2013.6677446","DOIUrl":"https://doi.org/10.1109/URAI.2013.6677446","url":null,"abstract":"This paper presents a method which can detect multi-pose faces for robot. To overcome a disadvantage of conventional single-view face detection. we compute hyperplane using Linear Discriminant Analysis (LDA). These hyperplane are used to separate two different classes finely. This method could reduce false positive rate on branching nodes significantly, as well as the number of unnecessary branches. Consequently, overall speed of the detector could be improved about 24 percent compared to the case without hyperplane partition.","PeriodicalId":431699,"journal":{"name":"2013 10th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126039905","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：