On the scalability of robot localization using high-dimensional features

This study provides an investigation of scalability of mobile robot localization. In recent years, inference algorithms based on map-matching have proved their superior performance in large-scale environments. In this paper, the scalability is augmented by an ANN retrieval of high-dimensional descriptive features. The proposed algorithm is then exhaustively evaluated using largesize real maps, including over 100K feature maps.

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: Takeshi Ueda, Kanji Tanaka
• Keywords: Computer Vision, ICPR 2008, Largesize Real Maps, Mobile Robot Localization, Scalability