Pub Date : 2011-11-01DOI: 10.1109/URAI.2011.6145870
Sung-Wan Kim, Ji-Yong Lee, Doik Kim, Bum-Jae You, N. Doh
In this paper, a method for accurate human localization using a sequential fusion of sound and vision is proposed. Although the sound localization alone works well in most cases, there are situations such as noisy environment and small inter-microphone distance, which may produce wrong or poor results. A vision system also has deficiency, such as limited visual field. To solve these problems we propose a method that combines sound localization and vision in real time. Particularly, a robot finds rough location of the speaker via sound source localization, and then using vision to increase the accuracy of the location. Experimental results show that the proposed method is more accurate and reliable than the results of pure sound localization.
{"title":"Human localization based on the fusion of vision and sound system","authors":"Sung-Wan Kim, Ji-Yong Lee, Doik Kim, Bum-Jae You, N. Doh","doi":"10.1109/URAI.2011.6145870","DOIUrl":"https://doi.org/10.1109/URAI.2011.6145870","url":null,"abstract":"In this paper, a method for accurate human localization using a sequential fusion of sound and vision is proposed. Although the sound localization alone works well in most cases, there are situations such as noisy environment and small inter-microphone distance, which may produce wrong or poor results. A vision system also has deficiency, such as limited visual field. To solve these problems we propose a method that combines sound localization and vision in real time. Particularly, a robot finds rough location of the speaker via sound source localization, and then using vision to increase the accuracy of the location. Experimental results show that the proposed method is more accurate and reliable than the results of pure sound localization.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121816342","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 : 2011-11-01DOI: 10.1109/URAI.2011.6145931
H. Wicaksono
Behavior based architecture gives robot fast and reliable action. If there are many behaviors in robot, behavior coordination is needed. Subsumption architecture is behavior coordination method that give quick and robust response. Learning mechanism improve robot's performance in handling uncertainty. Q learning is popular reinforcement learning method that has been used in robot learning because it is simple, convergent and off policy. In this paper, Q learning will be used as learning mechanism for obstacle avoidance behavior in autonomous robot navigation. Learning rate of Q learning affect robot's performance in learning phase. As the result, Q learning algorithm is successfully implemented in a physical robot with its imperfect environment.
{"title":"Q learning behavior on autonomous navigation of physical robot","authors":"H. Wicaksono","doi":"10.1109/URAI.2011.6145931","DOIUrl":"https://doi.org/10.1109/URAI.2011.6145931","url":null,"abstract":"Behavior based architecture gives robot fast and reliable action. If there are many behaviors in robot, behavior coordination is needed. Subsumption architecture is behavior coordination method that give quick and robust response. Learning mechanism improve robot's performance in handling uncertainty. Q learning is popular reinforcement learning method that has been used in robot learning because it is simple, convergent and off policy. In this paper, Q learning will be used as learning mechanism for obstacle avoidance behavior in autonomous robot navigation. Learning rate of Q learning affect robot's performance in learning phase. As the result, Q learning algorithm is successfully implemented in a physical robot with its imperfect environment.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131816456","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 : 2011-11-01DOI: 10.1109/URAI.2011.6146020
Dongil Park, C. Park, Yijun Yoo, Hyunmin Do, J. Kyung
In the thin film solar cell production system, it is a very important task to handle the large size solar cell substrate. Many handling robots have been developed and applied in the manufacturing line. As the substrate size gets larger, dynamic analysis and vibration control including flexible forks becomes very important. Precise position control including the vibration of forks and the substrate is very important because solar cell substrate is three to five times heavier than LCD glass substrate. In the paper, we analyzed dynamic motion of the robot and vibration of end-effector including flexible forks using RecurDyn. Motion trajectory is based on tact time in the real production line and motion simulation is performed in the various conditions.
{"title":"Dynamic analysis of beam type substrate handling robot in solar cell manufacturing","authors":"Dongil Park, C. Park, Yijun Yoo, Hyunmin Do, J. Kyung","doi":"10.1109/URAI.2011.6146020","DOIUrl":"https://doi.org/10.1109/URAI.2011.6146020","url":null,"abstract":"In the thin film solar cell production system, it is a very important task to handle the large size solar cell substrate. Many handling robots have been developed and applied in the manufacturing line. As the substrate size gets larger, dynamic analysis and vibration control including flexible forks becomes very important. Precise position control including the vibration of forks and the substrate is very important because solar cell substrate is three to five times heavier than LCD glass substrate. In the paper, we analyzed dynamic motion of the robot and vibration of end-effector including flexible forks using RecurDyn. Motion trajectory is based on tact time in the real production line and motion simulation is performed in the various conditions.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133063483","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 : 2011-11-01DOI: 10.1109/URAI.2011.6146025
Inwook Shim, Yungeun Choe, M. Chung
In recent year, much progress has been made in outdoor 3D mapping. However, 3D mapping in real time is still a daunting challenge in urban environment. This paper addresses the problem of 3D mapping from 3D laser scans in urban environments in real time. To do this, we proposed geometric featured voxel which can efficiently represent 3D urban structure without loss of geometric properties. For evaluation of the proposed voxel, we use Oakland dataset.
{"title":"3D mapping in urban environment using geometric featured voxel","authors":"Inwook Shim, Yungeun Choe, M. Chung","doi":"10.1109/URAI.2011.6146025","DOIUrl":"https://doi.org/10.1109/URAI.2011.6146025","url":null,"abstract":"In recent year, much progress has been made in outdoor 3D mapping. However, 3D mapping in real time is still a daunting challenge in urban environment. This paper addresses the problem of 3D mapping from 3D laser scans in urban environments in real time. To do this, we proposed geometric featured voxel which can efficiently represent 3D urban structure without loss of geometric properties. For evaluation of the proposed voxel, we use Oakland dataset.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115601858","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 : 2011-11-01DOI: 10.1109/URAI.2011.6145913
Y. Lee, Hyunah Seo
The objective of this study was to provide basic materials to plan effective development of curriculums for the integration of R-learning education in the early childhood school system. In order to investigate the perception and demand of R-learning, we conducted a questionnaire survey of 30 professors and 482 pre-service teachers at the Department of Early Childhood Education in colleges throughout Korea. Moreover, in order to survey the operation and current state of curriculums related to R-learning at the Department of Early Childhood Education, we analyzed the homepages of the Department of Early Childhood Education in 104 colleges offering computer and multimedia curriculums among 165 colleges in Korea. According to the results, first, with regard to the perception of R-learning curriculums, all of the early childhood education professors and pre-service teachers recognized the necessity of R-learning curriculums, and concerning problems in the organization and operation of R-learning curriculums, they mentioned the excessive number of curriculums to be completed within the course of the department and whether such curriculums would take an important part as major subjects. Second, with regard to the operation of curriculums related to computer and multimedia at the Department of Early Childhood Education, 104 (63%) out of 165 colleges were operating such curriculums at the Department of Early Childhood Education. Third, based on the analysis of the demand and current state of R-learning curriculums, we proposed a model for the integration of R-learning curriculums into existing related curriculums. From the results of this study, we expect to introduce robot-based education into the field of early childhood education early through enhancing in-service and pre-service teachers' positive attitude toward R-learning and their skills in robot-based education, and to make mid-term and long-term strategies for integrating robot-based education into early childhood education courses.
{"title":"A basic study for the development of R-learning curriculums in the Early Childhood school system","authors":"Y. Lee, Hyunah Seo","doi":"10.1109/URAI.2011.6145913","DOIUrl":"https://doi.org/10.1109/URAI.2011.6145913","url":null,"abstract":"The objective of this study was to provide basic materials to plan effective development of curriculums for the integration of R-learning education in the early childhood school system. In order to investigate the perception and demand of R-learning, we conducted a questionnaire survey of 30 professors and 482 pre-service teachers at the Department of Early Childhood Education in colleges throughout Korea. Moreover, in order to survey the operation and current state of curriculums related to R-learning at the Department of Early Childhood Education, we analyzed the homepages of the Department of Early Childhood Education in 104 colleges offering computer and multimedia curriculums among 165 colleges in Korea. According to the results, first, with regard to the perception of R-learning curriculums, all of the early childhood education professors and pre-service teachers recognized the necessity of R-learning curriculums, and concerning problems in the organization and operation of R-learning curriculums, they mentioned the excessive number of curriculums to be completed within the course of the department and whether such curriculums would take an important part as major subjects. Second, with regard to the operation of curriculums related to computer and multimedia at the Department of Early Childhood Education, 104 (63%) out of 165 colleges were operating such curriculums at the Department of Early Childhood Education. Third, based on the analysis of the demand and current state of R-learning curriculums, we proposed a model for the integration of R-learning curriculums into existing related curriculums. From the results of this study, we expect to introduce robot-based education into the field of early childhood education early through enhancing in-service and pre-service teachers' positive attitude toward R-learning and their skills in robot-based education, and to make mid-term and long-term strategies for integrating robot-based education into early childhood education courses.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117067813","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 : 2011-11-01DOI: 10.1109/URAI.2011.6145990
H. Phan, Q. Nguyen, H. Park, N. Goo, D. Byun
In recent years, there has been a lot of progress in developing Flapping-Wing Micro Air Vehicles (FW-MAVs) [1–2]. Most of them were designed for low Reynolds numbers environment (in the range of 5,000 to 10,000 [3]). Therefore, many researchers have been paying attention to principle of insect flight for potential application to improve FW-MAVs or to develop even smaller system, called Nano Air Vehicles (NAVs) [4].
{"title":"Improvement of stability for vertical take-off of an insect-mimicking flapping-wing system","authors":"H. Phan, Q. Nguyen, H. Park, N. Goo, D. Byun","doi":"10.1109/URAI.2011.6145990","DOIUrl":"https://doi.org/10.1109/URAI.2011.6145990","url":null,"abstract":"In recent years, there has been a lot of progress in developing Flapping-Wing Micro Air Vehicles (FW-MAVs) [1–2]. Most of them were designed for low Reynolds numbers environment (in the range of 5,000 to 10,000 [3]). Therefore, many researchers have been paying attention to principle of insect flight for potential application to improve FW-MAVs or to develop even smaller system, called Nano Air Vehicles (NAVs) [4].","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115435302","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 : 2011-11-01DOI: 10.1109/URAI.2011.6145935
J. Oh, E. Im, Kyoungro Yoon
Unmanned Aerial Vehicles (UAV) are finding their way to a wide range of safety-critical missions. Our collaborative research team of computer scientists and aerospace engineers has worked on developing hardware and software of UAV. One of vital components in software used in UAV is image stabilization. The constantly-shaking images taken from the UAV, resulted from the vehicle's motion, need to be stabilized to perform its mission. In this paper, we present our implementation of image stabilization software. Our research is focused on using state-of-the-art Graphic Processing Unit (GPU) to improve the performance of the image stabilization software. The stabilizer estimates motion of the vehicle by calculating optical flow between successive two frames. In this study, we parallelized the calculation of the optical flow, which is identified as a computational bottleneck of the entire image stabilization process. Using the massive parallelism of NVIDIA C2060 GPU with 448 cores, we could improve the overall performance of image stabilizer.
{"title":"Optical flow computation on a heterogeneous platform","authors":"J. Oh, E. Im, Kyoungro Yoon","doi":"10.1109/URAI.2011.6145935","DOIUrl":"https://doi.org/10.1109/URAI.2011.6145935","url":null,"abstract":"Unmanned Aerial Vehicles (UAV) are finding their way to a wide range of safety-critical missions. Our collaborative research team of computer scientists and aerospace engineers has worked on developing hardware and software of UAV. One of vital components in software used in UAV is image stabilization. The constantly-shaking images taken from the UAV, resulted from the vehicle's motion, need to be stabilized to perform its mission. In this paper, we present our implementation of image stabilization software. Our research is focused on using state-of-the-art Graphic Processing Unit (GPU) to improve the performance of the image stabilization software. The stabilizer estimates motion of the vehicle by calculating optical flow between successive two frames. In this study, we parallelized the calculation of the optical flow, which is identified as a computational bottleneck of the entire image stabilization process. Using the massive parallelism of NVIDIA C2060 GPU with 448 cores, we could improve the overall performance of image stabilizer.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121726715","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 : 2011-11-01DOI: 10.1109/URAI.2011.6145991
Kai Zhou, M. Zillich, M. Vincze
This work presents the results of 5 days of project work carried out as part of the 2011 CogX Spring School. The task to be solved was to program a mobile robot to train a set of objects, locate a subset of these in a room, and to pick up and return them to a defined drop-off zone.
{"title":"Mobile manipulation: Bring back the cereal box video proceedings of the 2011 CogX Spring School","authors":"Kai Zhou, M. Zillich, M. Vincze","doi":"10.1109/URAI.2011.6145991","DOIUrl":"https://doi.org/10.1109/URAI.2011.6145991","url":null,"abstract":"This work presents the results of 5 days of project work carried out as part of the 2011 CogX Spring School. The task to be solved was to program a mobile robot to train a set of objects, locate a subset of these in a room, and to pick up and return them to a defined drop-off zone.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122604000","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 : 2011-11-01DOI: 10.1109/URAI.2011.6146006
Sang Un Park, Inwook Shim, M. Chung
3D mapping and expression of the environment are very important with various applications in many different fields. Among the various sensors (vision sensor, infrared sensor, and LiDAR (Light Detection and Ranging) sensor), we used the LiDAR sensor in this paper because its accuracy is good and easy to handle. There exist holes in the result of 3D reconstruction. When these holes are filled, improved results of localization, and path planning are expected. We propose a contour based sampling algorithm to fill holes. It uses the information from regions near the holes for the prediction, and the results confirm that the filled regions look similar to the real environment.
{"title":"Hole filled 3D map using mobile robots in the urban environment","authors":"Sang Un Park, Inwook Shim, M. Chung","doi":"10.1109/URAI.2011.6146006","DOIUrl":"https://doi.org/10.1109/URAI.2011.6146006","url":null,"abstract":"3D mapping and expression of the environment are very important with various applications in many different fields. Among the various sensors (vision sensor, infrared sensor, and LiDAR (Light Detection and Ranging) sensor), we used the LiDAR sensor in this paper because its accuracy is good and easy to handle. There exist holes in the result of 3D reconstruction. When these holes are filled, improved results of localization, and path planning are expected. We propose a contour based sampling algorithm to fill holes. It uses the information from regions near the holes for the prediction, and the results confirm that the filled regions look similar to the real environment.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123825533","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 : 2011-11-01DOI: 10.1109/URAI.2011.6145968
Min-Goo Choi, Nak-Yoon Choi, Young-Lim Choi, Jong-Wook Kim
This paper proposes a new approach to generate joint trajectories of a humanoid robot for kicking forward, which is one of the basic motions in Taekwondo. This type of motion generation is regarded difficult because of high dimensional complexities under the Denavit-Hartenberg kinematic convention especially in case of the humanoid robot. However, the projection based kinematics enables us to intuitively schedule trajectories of joint motors by mimicking human's kicking motion. The forward kick is divided into three postures with corresponding joint motor angles, and the motor trajectories are generated to pass them, to maximize kicking power, and to maintain standing stability. This is carried out by computer simulation, which will be realized with a small humanoid robot.
{"title":"Joint trajectory generation of humanoid robot's front kick","authors":"Min-Goo Choi, Nak-Yoon Choi, Young-Lim Choi, Jong-Wook Kim","doi":"10.1109/URAI.2011.6145968","DOIUrl":"https://doi.org/10.1109/URAI.2011.6145968","url":null,"abstract":"This paper proposes a new approach to generate joint trajectories of a humanoid robot for kicking forward, which is one of the basic motions in Taekwondo. This type of motion generation is regarded difficult because of high dimensional complexities under the Denavit-Hartenberg kinematic convention especially in case of the humanoid robot. However, the projection based kinematics enables us to intuitively schedule trajectories of joint motors by mimicking human's kicking motion. The forward kick is divided into three postures with corresponding joint motor angles, and the motor trajectories are generated to pass them, to maximize kicking power, and to maintain standing stability. This is carried out by computer simulation, which will be realized with a small humanoid robot.","PeriodicalId":385925,"journal":{"name":"2011 8th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125407103","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：