Pub Date : 2010-07-26DOI: 10.1109/SSRR.2010.5981548
Cheng Qian, Yingqiu Xu, Hui Shen, Yingzi Tan
Some line matching algorithms have been proposed for the laser scan matching problem. But lots of them do the matching between current scan frame and the last one, rather than current frame and the global map. This work proposes a real-time laser scan matching method named Global Line Matching, which matches current scan frame to the global map, leading to a better result. This paper presents the algorithm in detail and shows some applications based on simultaneous localization and mapping (SLAM). Results on a simulated environment (USARSim [1]) are demonstrated, showing that this algorithm is capable of mapping unmodified indoor environment reliably.
{"title":"A Global Line Matching algorithm for 2D laser scan matching in regular environment","authors":"Cheng Qian, Yingqiu Xu, Hui Shen, Yingzi Tan","doi":"10.1109/SSRR.2010.5981548","DOIUrl":"https://doi.org/10.1109/SSRR.2010.5981548","url":null,"abstract":"Some line matching algorithms have been proposed for the laser scan matching problem. But lots of them do the matching between current scan frame and the last one, rather than current frame and the global map. This work proposes a real-time laser scan matching method named Global Line Matching, which matches current scan frame to the global map, leading to a better result. This paper presents the algorithm in detail and shows some applications based on simultaneous localization and mapping (SLAM). Results on a simulated environment (USARSim [1]) are demonstrated, showing that this algorithm is capable of mapping unmodified indoor environment reliably.","PeriodicalId":371261,"journal":{"name":"2010 IEEE Safety Security and Rescue Robotics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116033492","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 : 2010-07-26DOI: 10.1109/SSRR.2010.5981551
J. Silva, Vítor Matos, C. Santos
Trajectory modulation and generation are two fundamental issues in the path planning problem in autonomous robotics, specially considering temporal stabilization of the generated movements. This is a very critical issue in several robotic tasks including: catching, hitting, and human-robot scenarios.
{"title":"Generating trajectories with temporal constraints for an autonomous robot","authors":"J. Silva, Vítor Matos, C. Santos","doi":"10.1109/SSRR.2010.5981551","DOIUrl":"https://doi.org/10.1109/SSRR.2010.5981551","url":null,"abstract":"Trajectory modulation and generation are two fundamental issues in the path planning problem in autonomous robotics, specially considering temporal stabilization of the generated movements. This is a very critical issue in several robotic tasks including: catching, hitting, and human-robot scenarios.","PeriodicalId":371261,"journal":{"name":"2010 IEEE Safety Security and Rescue Robotics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133554710","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 : 2010-07-26DOI: 10.1109/SSRR.2010.5981562
T. Y. Kim, G. Sung, J. Lyou
This paper presents a vision-based off-road terrain classification method that is robust despite large environmental variations caused by seasonal or weather changes. In order to account for an overall image feature variation, we adopted environmental sensors, and to train a neural network based classifier, constructed a database according to environmental conditions. Robust classification could be achieved by selecting the training parameter set best suited for each environmental state. Also, we propose a hardware architecture that enables distributed parallel processing for real- time implementation of the present algorithm. Experimental results for real off-road images show that in spite of dissimilar conditions, degradation of classification performance could be minimized by replacing the nearest parameters.
{"title":"Robust terrain classification by introducing environmental sensors","authors":"T. Y. Kim, G. Sung, J. Lyou","doi":"10.1109/SSRR.2010.5981562","DOIUrl":"https://doi.org/10.1109/SSRR.2010.5981562","url":null,"abstract":"This paper presents a vision-based off-road terrain classification method that is robust despite large environmental variations caused by seasonal or weather changes. In order to account for an overall image feature variation, we adopted environmental sensors, and to train a neural network based classifier, constructed a database according to environmental conditions. Robust classification could be achieved by selecting the training parameter set best suited for each environmental state. Also, we propose a hardware architecture that enables distributed parallel processing for real- time implementation of the present algorithm. Experimental results for real off-road images show that in spite of dissimilar conditions, degradation of classification performance could be minimized by replacing the nearest parameters.","PeriodicalId":371261,"journal":{"name":"2010 IEEE Safety Security and Rescue Robotics","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121443412","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 : 2010-07-26DOI: 10.1109/SSRR.2010.5981568
T. Kinugasa, T. Akagi, K. Ishii, T. Haji, K. Yoshida, Y. Otani, H. Amano, R. Hayashi, K. Tokuda, K. Osuka
We have proposed Flexible Mono-tread mobile Track (FMT) as a mobile mechanism for hazardous environment such as disaster area. FMT has only one track which can flex in three dimension. Generally speaking, one has to teleoperate robots under invisible condition. In order to operate the robots skillfully, it is necessary to detect not only condition around the robots and its position but also posture of the robots at any time. Flexed posture of FMT decides turning radius and direction, it is very important to know its posture, accordingly. FMT has a vertebral structure composed of vertebrae as rigid body and intervertebral disks made by flexible devices such as rubber cylinder and spring. Since the intervertebral disks flex in three dimension, it is not easy for traditional sensors such as potentiometers, rotary encoders and range finders to measure its deformation. The purpose of the paper, therefore, is to measure flexed posture of FMT using a new flexible displacement sensor. We prove that the flexed posture of FMT with five intervertebral disks can be detected through experiment.
{"title":"Measurement of flexed posture for Flexible Mono-tread mobile Track using new flexible displacement sensor","authors":"T. Kinugasa, T. Akagi, K. Ishii, T. Haji, K. Yoshida, Y. Otani, H. Amano, R. Hayashi, K. Tokuda, K. Osuka","doi":"10.1109/SSRR.2010.5981568","DOIUrl":"https://doi.org/10.1109/SSRR.2010.5981568","url":null,"abstract":"We have proposed Flexible Mono-tread mobile Track (FMT) as a mobile mechanism for hazardous environment such as disaster area. FMT has only one track which can flex in three dimension. Generally speaking, one has to teleoperate robots under invisible condition. In order to operate the robots skillfully, it is necessary to detect not only condition around the robots and its position but also posture of the robots at any time. Flexed posture of FMT decides turning radius and direction, it is very important to know its posture, accordingly. FMT has a vertebral structure composed of vertebrae as rigid body and intervertebral disks made by flexible devices such as rubber cylinder and spring. Since the intervertebral disks flex in three dimension, it is not easy for traditional sensors such as potentiometers, rotary encoders and range finders to measure its deformation. The purpose of the paper, therefore, is to measure flexed posture of FMT using a new flexible displacement sensor. We prove that the flexed posture of FMT with five intervertebral disks can be detected through experiment.","PeriodicalId":371261,"journal":{"name":"2010 IEEE Safety Security and Rescue Robotics","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124663210","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：