SLAM for Flight Through Urban Environments Using Dimensionality Reduction

Abstract

Robotic mapping is an enabling technology for the navigation of autonomous vehicles. The problem of estimating both a vehicle’s state and a map of its environment is referred to as Simultaneous Localization and Mapping (SLAM). This paper presents a SLAM framework suitable of a Micro Air Vehicle (MAV) equipped only with a monocular camera. Structure from Motion (SFM) is employed to infer three-dimensional environment information from a stream of digital images. A dimensionality reduction step generates a geometric model of the vehicle’s surroundings by exploiting the structure inherent in urban settings. The focus of this paper is to formulate a vision-only SLAM framework for building maps that are amenable to motion planning algorithms to enable autonomous navigation. Simulation results are presented to demonstrate the SLAM algorithm. I.