{"title":"Vision-based pose estimation for indoor navigation of unmanned micro aerial vehicle based on the 3D model of environment","authors":"Alexander Buyval, Mikhail Gavrilenkov","doi":"10.1109/MEACS.2015.7414857","DOIUrl":null,"url":null,"abstract":"The main function of unmanned micro aerial vehicle (UMAV) is localization. If the robot knows where it is, it will be able to create a correct route and to complete it task. An indoor environment doesn't allow using GPS/GLONASS sensors on robots. Also other sensors like LIDAR and ultrasonic ranges has its own disadvantages. In this paper we suggest to use monocular camera as main sensor. The image from camera is used to extract edges and then to compare them with edges from known 3D model of environment. To estimate a final hypothesis about robot localization we used a particle filter. Finally, we have developed our localization system as ROS based subsystem and used the Gazebo simulator for testing.","PeriodicalId":423038,"journal":{"name":"2015 International Conference on Mechanical Engineering, Automation and Control Systems (MEACS)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Mechanical Engineering, Automation and Control Systems (MEACS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MEACS.2015.7414857","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
The main function of unmanned micro aerial vehicle (UMAV) is localization. If the robot knows where it is, it will be able to create a correct route and to complete it task. An indoor environment doesn't allow using GPS/GLONASS sensors on robots. Also other sensors like LIDAR and ultrasonic ranges has its own disadvantages. In this paper we suggest to use monocular camera as main sensor. The image from camera is used to extract edges and then to compare them with edges from known 3D model of environment. To estimate a final hypothesis about robot localization we used a particle filter. Finally, we have developed our localization system as ROS based subsystem and used the Gazebo simulator for testing.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
