Error analysis and attitude observability of a monocular GPS/visual odometry integrated navigation filter

  • Authors:

  • Damien Dusha;Luis Mejias

  • Affiliations:

  • Australian Research Centre for Aerospace Automation, Queensland University of Technology, Brisbane, Australia;Australian Research Centre for Aerospace Automation, Queensland University of Technology, Brisbane, Australia

  • Venue:
  • International Journal of Robotics Research
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we present a method for the recovery of position and absolute attitude (including pitch, roll and yaw) using a novel fusion of monocular visual odometry and GPS measurements in a similar manner to a classic loosely coupled GPS/INS error state navigation filter. The proposed filter does not require additional restrictions or assumptions such as platform-specific dynamics, map matching, feature tracking, visual loop closing, gravity vector or additional sensors such as an inertial measurement unit or magnetic compass. An observability analysis of the proposed filter is performed, showing that the scale factor, position and attitude errors are fully observable under acceleration that is non-parallel to the velocity vector in the navigation frame. The observability properties of the proposed filter are demonstrated using numerical simulations. We conclude the article with an implementation of the proposed filter using real flight data collected from a Cessna 172 equipped with a downwards-looking camera and GPS, showing the feasibility of the algorithm in real-world conditions.