The problem of gas detection is relevant to many real-world applications, such as leak detection in industrial settings and landfill monitoring. In this thesis we address the problem of gas detection in large areas with a mobile robotic platform equipped with a remote gas sensor. We propose an online algorithm based on the concept of Next-Best View for solving the coverage problem to which the gas detection problem can be reduced. To demonstrate the applicability of our method to real-world environments, we performed a large number of experiments, both in simulation and in a real environment. Our approach proves to be highly efficient in terms of computational requirements and to achieve good performance.
Il problema legato al rilevamento del gas `e di fondamentale importanza in molte applicazioni, quali l’identificazione delle perdite in ambienti industri- ali e il monitoraggio delle discariche. In questa tesi affrontiamo il problema del rilevamento del gas in ampi spazi interni con una piattaforma robotica mobile, equipaggiata con un sensore gas remoto. Proponiamo un algoritmo online basato sul concetto di Next-Best-View per risolvere il problema di copertura a cui il problema del rilevamento del gas pu`o essere ridotto. Per dimostrare l’applicabilit` a del nostro metodo abbiamo svolto un elevato nu- mero di esperimenti, sia simulati che in un ambiente reale. Il nostro ap- proccio ha dato prova di essere altamente efficiente in termini di risorse computazionali, e di raggiungere buone prestazioni.
A next-best-smell approach for remote gas detection with a mobile robot
POLVARA, RICCARDO;TRABATTONI, MARCO
2014/2015
Abstract
The problem of gas detection is relevant to many real-world applications, such as leak detection in industrial settings and landfill monitoring. In this thesis we address the problem of gas detection in large areas with a mobile robotic platform equipped with a remote gas sensor. We propose an online algorithm based on the concept of Next-Best View for solving the coverage problem to which the gas detection problem can be reduced. To demonstrate the applicability of our method to real-world environments, we performed a large number of experiments, both in simulation and in a real environment. Our approach proves to be highly efficient in terms of computational requirements and to achieve good performance.File | Dimensione | Formato | |
---|---|---|---|
2015_09_Polvara_Trabattoni.pdf
accessibile in internet per tutti
Descrizione: "Definitive" Thesis
Dimensione
1.76 MB
Formato
Adobe PDF
|
1.76 MB | Adobe PDF | Visualizza/Apri |
I documenti in POLITesi sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/10589/112563