This paper presents an unconventional approach to vision-guided autonomous navigation. The system recalls information about scenes and navigational experience using content-based retrieval from a visual database. To achieve a high applicability and adaptability to various road types, we do not impose a priori scene features, such as road edges, that the system must use, but rather the system automatically selects features from images during supervised learning. A new self-organizing scheme called recursive partition tree (RPT) is used for automatic construction of a vision-and-control database, which quickly prunes the data set in the content-based search and results in a low time complexity of log(n) for retrieval from a database of size n. Experimental results are reported in both indoor and outdoor navigation.
Autonomous navigation through case-based learning
01.01.1995
744208 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Autonomous Navigation Through Case-Based Learning
British Library Conference Proceedings | 1995
|Learning for Autonomous Navigation
NTRS | 2005
|Learning for autonomous navigation
NTRS | 2005
|