Line Segment-Based Indoor Mapping with Salient Line Feature Extraction

Abstract

We present a method of simultaneous localization and mapping (SLAM) in a large indoor environment using a Rao-Blackwellized particle filter (RBPF) along with a line segment as a landmark. To represent the environment in a compact form, we use only two end points of a line segment, thus reducing computational cost in modeling line segment uncertainty. With a modified scan point clustering method, the proposed adaptive iterative end point fitting contributes to the estimation of line parameters by considering noisy scan points near end points. Thus, by line segment matching the robot is localized well in a local frame. We also introduce an online and offline method of global line merging, which provides a more compact map by removing spurious lines and merging collinear lines. Each of our approaches is efficiently integrated into the proposed RBPF-SLAM framework. In experiments with well-known data sets, the proposed method provides reliable SLAM and compact map representation even in a cluttered environment.