FusionCore is a production-grade ROS 2 sensor fusion library. A 23-state UKF fuses GPS, IMU, and wheel odometry with adaptive noise estimation (no manual Q tuning), chi-squared outlier rejection that catches GPS multipath spikes before they move the estimate, inertial coast through GPS dropouts, and ECEF-native GPS that works anywhere on Earth. Benchmarked against robot_localization on the NCLT outdoor dataset: ahead on 10 of 12 sequences. ROS 2, Apache 2.0.

FusionCore is a production-grade ROS 2 sensor fusion library. It runs a 22-state UKF fusing GPS, IMU, and wheel odometry with adaptive noise estimation (no manual Q tuning), Mahalanobis outlier rejection for GPS spikes and IMU glitches, and ECEF-native GPS handling that works at any scale. Benchmarked against robot_localization on the NCLT outdoor driving dataset: FusionCore wins on 5 of 6 sequences, up to 4 × lower ATE. Apache 2.0.