Metric maps, like occupancy grids, are the most common way to represent indoor environments in mobile robotics. Although accurate for navigation and localization, metric maps contain little knowledge about the structure of the buildings they represent. However, if explicitly identified and represented, this knowledge can be exploited in several tasks, such as semantic mapping, place categorization, path planning, human robot communication, and task allocation. The layout of a building is an abstract geometrical representation that models walls as line segments and rooms as polygons. In this paper, we propose a method to reconstruct two-dimensional layouts of buildings starting from the corresponding metric maps. In this way, our method is able to find regularities within a building, abstracting from the possibly noisy information of the metric map. Experimental results show that our approach performs effectively and robustly on different types of input metric maps, characterized by noise, clutter, and partial data.
Extracting Structure of Buildings Using Layout Reconstruction / M. Luperto, F. Amigoni (ADVANCES IN INTELLIGENT SYSTEMS AND COMPUTING). - In: Intelligent Autonomous Systems 15 / [a cura di] M. Strand, R. Dillmann, E. Menegatti, S. Ghidoni. - Prima edizione. - [s.l] : Springer, 2019. - ISBN 9783030013691. - pp. 652-667 (( convegno Intelligent Autonomous Systems 15 tenutosi a Baden-Baden nel 2018 [10.1007/978-3-030-01370-7_51].
Extracting Structure of Buildings Using Layout Reconstruction
M. Luperto
Primo
;
2019
Abstract
Metric maps, like occupancy grids, are the most common way to represent indoor environments in mobile robotics. Although accurate for navigation and localization, metric maps contain little knowledge about the structure of the buildings they represent. However, if explicitly identified and represented, this knowledge can be exploited in several tasks, such as semantic mapping, place categorization, path planning, human robot communication, and task allocation. The layout of a building is an abstract geometrical representation that models walls as line segments and rooms as polygons. In this paper, we propose a method to reconstruct two-dimensional layouts of buildings starting from the corresponding metric maps. In this way, our method is able to find regularities within a building, abstracting from the possibly noisy information of the metric map. Experimental results show that our approach performs effectively and robustly on different types of input metric maps, characterized by noise, clutter, and partial data.File | Dimensione | Formato | |
---|---|---|---|
IAS_15.pdf
accesso riservato
Tipologia:
Pre-print (manoscritto inviato all'editore)
Dimensione
2.84 MB
Formato
Adobe PDF
|
2.84 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.