Robotic Mapping: A Survey

ABSTRACT

This article provides a comprehensive introduction into the field of robotic mapping, with a focus on indoor mapping. It describes and compares various probabilistic techniques, as they are presently being applied to a vast array of mobile robot mapping problems. The history of robotic mapping is also described, along with an extensive list of open research problems.

Keywords: Bayes filters, robotic mapping, exploration, expectation maximization algorithm, Kalman filters, mobile robots

INTRODUCTION

Robotic mapping has been a highly active research area in robotics and AI for at least two decades. Robotic mapping addresses the problem of acquiring spatial models of physical environments through mobile robots. The mapping problem is generally regarded as one of the most important problems in the pursuit of building truly autonomous mobile robots. Despite significant progress in this area, it still poses great challenges. At present, we have robust methods for mapping environments that are static, structured, and of limited size. Mapping unstructured, dynamic, or large-scale environments remains largely an open research problem.

This article attempts to provide a comprehensive overview of the state of the art in robotic mapping, with a focus on indoor environments. Virtually all state-of-the-art robotic mapping algorithms are probabilistic. Some algorithms are incremental, and hence can be run in real time, whereas others require multiple passes through the data. Some algorithms require exact pose information to build a map, whereas others can do so using odometry measurements. Some algorithms are equipped to handle correspondence problems between data recorded at different points in time, whereas others require features to carry signatures that makes them uniquely identifiable.

When writing this article, we tried to keep the level of mathematics at a minimum, focusing instead on the intuition behind the different techniques. However, some mathematical notation was deemed necessary to communicate the basic concepts in a crisp way. The serious reader is invited to read some of the articles referenced in this paper, which discuss many of the ideas presented here in more depth.

DOWNLOAD....

Sebastian Thrun February 2002 CMU-CS-02-111

School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213

Detail...