An implementation of SLAM with extended Kalman filter
This paper discusses an implementation of Extended Kalman filter (EKF) in performing Simultaneous Localization and Mapping (SLAM). The implementation is divided into software and hardware phases. The software implementation applies EKF using Python on a library dataset to produce a map of the suppos...
保存先:
| 主要な著者: | , |
|---|---|
| フォーマット: | 論文 |
| 出版事項: |
Institute of Electrical and Electronics Engineers Inc.
2017
|
| オンライン･アクセス: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85011977071&doi=10.1109%2fICIAS.2016.7824105&partnerID=40&md5=212572503d8af499d137e71d98366506 http://eprints.utp.edu.my/20172/ |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 要約: | This paper discusses an implementation of Extended Kalman filter (EKF) in performing Simultaneous Localization and Mapping (SLAM). The implementation is divided into software and hardware phases. The software implementation applies EKF using Python on a library dataset to produce a map of the supposed environment. The result was verified against the original map and found to be relatively accurate with minor inaccuracies. In the hardware implementation stage, real life data was gathered from an indoor environment via a laser range finder and a pair of wheel encoders placed on a mobile robot. The resulting map shows at least five marked inaccuracies but the overall form is passable. © 2016 IEEE. |
|---|