Urban navigation system improves location accuracy with smart sensing and robust estimation
SeA-RVINS: Semantic-Aware Tightly Coupled RTK-Visual-Inertial System with Correlation-Preserving Robust Estimation for Urban Navigation
Robotics
Summary
Finding exact positions in cities is hard because GPS signals can bounce off buildings and cameras can make mistakes when tracking objects. The authors developed a system called SeA-RVINS that combines GPS, cameras, and motion sensors to figure out locations more reliably. It uses smart software that ignores bad data and carefully checks connections over time to avoid errors. Tested on a 20-kilometer urban route, the system consistently kept location errors very low and worked almost all the time.
What this means in practice
- •For autonomous vehicle engineers: Improve precise vehicle positioning in urban areas by reducing location errors caused by GPS and visual sensor errors.
- •For robotics navigation teams: Enable robust urban robot navigation by tightly integrating satellite and visual-inertial sensor data with outlier rejection.
Authors
Wang Hu, Bo Wu
Abstract
Reliable absolute pose estimation in urban environments is undermined by outlier measurements and incorrect temporal associations that can persist in tightly coupled estimators. Global Navigation Satellite System (GNSS) observations provide globally referenced measurements but are prone to multipath effects. Visual-inertial sensing supplies local motion constraints, but false visual associations can corrupt the estimator. We present SeA-RVINS, a fixed-lag factor-graph Real-Time Kinematic (RTK) visual-inertial system for robust urban pose estimation. A semantic-aware learned stereo frontend rejects unreliable tracks before persistent landmarks enter the graph. For double-differenced GNSS measurements, SeA-RVINS applies Dynamic Covariance Scaling through configurable batch, scalar, and latent-pivot robust formulations while retaining the shared-pivot correlation structure. We propose a hybrid ambiguity-continuation strategy that shares one ambiguity state over short arcs with verified continuity and softly links successive arcs through random-walk factors. On an approximately 20-km route from the public TEX-CUP dataset, including about 50\% deep-urban driving, the latent-pivot configuration achieves 100\% availability and a 1.6-m maximum horizontal error, with 96.16\% and 99.90\% of epochs below 1.0 and 1.5 m, respectively. The implementation is released as open-source software