Contents I. Introduction
Simultaneous localization and mapping (SLAM) has been a field of study for many decades. From radars and range finders, to cameras and lasers, many modalities of SLAM have been developed to solve the fundamental problem of finding sensor poses in a global representation. The development of 2D laser scanners, while expensive, was a game changer that unlocked the mass deployment of service robots seen today. 2D SLAM and localization techniques have led the way for reliable and computationally efficient positioning in large scale environments for much of the last decade. As robot costs are being driven down to enable large scale fleets, sale to consumers, and application to new problems, the cost of laser scanners has become a significant bottleneck. Further, robots are now being deployed in multi-story construction sites, urban cities, and all-terrain areas not suitable for 2D techniques - regardless of sensor price. Robust and mature approaches relying on cameras and comparatively low cost RGB-D sensors will be crucial for enabling this next wave of robot applications.
