A tightly-coupled PPP/visual positioning method for fast initialization and effective continuity

Abstract

Precise Point Positioning (PPP) is one of the most widely used positioning methods, providing standalone positioning solutions with high accuracy. However, the algorithm usually requires tens of minutes to converge which makes the application restricted in many scenarios. The rapid developments of unmanned systems urge real-time positioning solutions with accuracy and continuity in complicated environments, where the GNSS observations get interrupted frequently. In view of this, we propose an integration positioning method tightly coupling PPP with visual localization. With the coordinates of the visual landmarks in the navigation frame measured priorly, the proposed method combines the observation equations of PPP and visual localizations providing accurate estimation of the position. Both simulation and real experiments are conducted to verify the effectiveness of the proposed method. With around five landmarks in sight simultaneously, the proposed method achieves its utmost performance to converge in seconds with a centimeter-level positioning accuracy, relatively better than the PPP-only method. The simulation based on real experiment data indicates that the proposed method keeps its output continuous and smooth when re-initialization happens once the observations of GNSS and visual get interrupted. The method offers positioning solutions with centimeter-level precision converging in 3–5 s, which indicates a promising application prospect in challenging environments in the future.