Scognamiglio, Vincenzo (2025) State Estimation and Autonomous Inspection of Industrial Sites with an Unmanned Aerial Vehicle. [Tesi di dottorato]
![[thumbnail of PhD_Thesis_State_Estimation_final_VS.pdf]](https://www.fedoa.unina.it/style/images/fileicons/other.png "PhD_Thesis_State_Estimation_final_VS.pdf") |
Documento PDF
PhD_Thesis_State_Estimation_final_VS.pdf Visibile a [TBR] Amministratori dell'archivio Download (69MB) | Richiedi una copia |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | State Estimation and Autonomous Inspection of Industrial Sites with an Unmanned Aerial Vehicle |
| Autori: | Autore Email Scognamiglio, Vincenzo vinsco3011@gmail.com |
| Data: | 5 Giugno 2025 |
| Numero di pagine: | 104 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Ingegneria Elettrica e delle Tecnologie dell'Informazione |
| Dottorato: | Information technology and electrical engineering |
| Ciclo di dottorato: | 37 |
| Coordinatore del Corso di dottorato: | nome email Russo, Stefano sterusso@unina.it |
| Tutor: | nome email Lippiello, Vincenzo [non definito] |
| Data: | 5 Giugno 2025 |
| Numero di pagine: | 104 |
| Parole chiave: | state estimation, navigation, odometry, autonomy, aerial robots |
| Settori scientifico-disciplinari del MIUR: | Area 09 - Ingegneria industriale e dell'informazione > ING-INF/04 - Automatica |
| Informazioni aggiuntive: | 37° Ciclo di Dottorato |
| Depositato il: | 06 Giu 2025 10:37 |
| Ultima modifica: | 12 Ago 2026 05:38 |
| URI: | https://www.fedoa.unina.it/id/eprint/16770 |
Abstract
This thesis investigates the exploitation of an autonomous UAV in visual inspection operations of industrial plants. Dealing with the lack of a GNSS signal, the agent needs to localize relying only on onboard capabilities, and then plan movements to accomplish the visual inspection tasks. The thesis will first focus on the design of a complete autonomous navigation framework suited for UAV which has been characterized for specific inspection missions. The deployment of an autonomous navigation framework in real-world tests helped to identify the odometry estimation problem as critical for long-term operations. To this end, the second part of the thesis will center on the study of the consistency of the EKF-based odometry estimation. This study will define a policy to detect when an EKF-based odometry source is degrading helping an adaptive filtering system to fuse gradually different sources of odometry.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
