Publication

Natural landmark detection for visually-guided robot navigation

Conference Article

Conference

Congress of the Italian Association for Artificial Intelligence (AI*IA)

Edition

10th

Pages

555-566

Doc link

http://dx.doi.org/10.1007/978-3-540-74782-6_48

File

Download the digital copy of the doc pdf document

Abstract

The main difficulty to attain fully autonomous robot navigation outdoors is the fast detection of reliable visual references, and their subsequent characterization as landmarks for immediate and unambiguous recognition. Aimed at speed, our strategy has been to track salient regions along image streams by just performing on-line pixel sampling. Persistent regions are considered good candidates for landmarks, which are then characterized by a set of subregions with given color and normalized shape. They are stored in a database for posterior recognition during the navigation process. Some experimental results showing landmark-based navigation of the legged robot Lauron III in an outdoor setting are provided.

Categories

automation.

Scientific reference

E. Celaya, J.L. Albarral, P. Jiménez and C. Torras. Natural landmark detection for visually-guided robot navigation, 10th Congress of the Italian Association for Artificial Intelligence, 2007, Roma, Italia, in Artificial Intelligence and Human-Oriented Computing, Vol 4733 of Lecture Notes in Computer Science, pp. 555-566, 2007, Springer, Berlin, Alemanya.