Layanan journal yang disediakan oleh Perpustakaan Universitas Gunadarma
| Judul Artikel | : | Solving Computational and Memory Requirements of Feature-Based Simultaneous Localization and Mapping Algorithms |
|---|---|---|
| Judul Terbitan | : | IEEE Transactions On Robotics And Automation |
| ISSN | : | 1042296X |
| Bahasa | : | ENG |
| Tempat Terbit | : | New - York |
| Tahun | : | 0000 |
| Volume | : | Vol. 19 Issue 4 0000 |
| Penerbit | : | IEEE |
| Frekuensi Penerbitan | : | |
| Penulis | : | Jose E. Guivant, Eduardo Mario Nebot |
| Abstraksi | : | This paper presents new algorithms to implement simulta us localization and mapping in environments with very large numbers features. The algorithms present an efficient solution to the full update aired by the compressed extended Kalman filter algorithm. It makes of the relative landmark representation to develop very close to op decorrelation solutions. With this approach, the memory and corn tional requirements are reduced from O(N2) to N O(N"NN), and Na proportional to the number of features in the map and fea close to the vehicle, respectively. Experimental results are presented verify the operation of the system when working in large outdoor envi ents. |
| Kata Kunci | : | Autonomous vehicles; Kalman filter; map building; navigation |
| Lokasi | : | p. 749 |
| Terakreditasi | : | belum |