Skip to main content
Engineering LibreTexts

12: RGB-D SLAM

  • Page ID
    14850
  • \( \newcommand{\vecs}[1]{\overset { \scriptstyle \rightharpoonup} {\mathbf{#1}} } \) \( \newcommand{\vecd}[1]{\overset{-\!-\!\rightharpoonup}{\vphantom{a}\smash {#1}}} \)\(\newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\) \( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\) \( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\) \( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\) \( \newcommand{\Span}{\mathrm{span}}\) \(\newcommand{\id}{\mathrm{id}}\) \( \newcommand{\Span}{\mathrm{span}}\) \( \newcommand{\kernel}{\mathrm{null}\,}\) \( \newcommand{\range}{\mathrm{range}\,}\) \( \newcommand{\RealPart}{\mathrm{Re}}\) \( \newcommand{\ImaginaryPart}{\mathrm{Im}}\) \( \newcommand{\Argument}{\mathrm{Arg}}\) \( \newcommand{\norm}[1]{\| #1 \|}\) \( \newcommand{\inner}[2]{\langle #1, #2 \rangle}\) \( \newcommand{\Span}{\mathrm{span}}\)\(\newcommand{\AA}{\unicode[.8,0]{x212B}}\)

    Range sensors have emerged as one of the most effective sensors to make robots autonomous. Unlike vision, range data makes the construction of a 3D model of the robot’s environment straightforward and the Velodyne sensor, that combines 64 scanning lasers into one package, was key in mastering the DARPA Grand Challenge. 3D range data has become even more important in robotics with the advent of cheap (priced at a tenth than the cheapest 2D laser scanner) RGB-D (color image plus depth) cameras. Point cloud data allows fitting of lines using RANSAC, which can serve as features in EKF-based localization, but can also be used for improving odometry, loopclosure detection, and mapping. The goals of this chapter are

    • introduce the Iterative Closest Point (ICP) algorithm
    • show how ICP can be improved by providing initial guesses via RANSAC
    • show how SIFT features can be used to improve point selection and loop-closure in ICP to achieve RGB-D mapping


    This page titled 12: RGB-D SLAM is shared under a CC BY-NC 4.0 license and was authored, remixed, and/or curated by Nikolaus Correll via source content that was edited to the style and standards of the LibreTexts platform; a detailed edit history is available upon request.