Wheel-Mounted/GNSS Fusion with AI-Aided Position Updates
2026-06-02 • Robotics
Robotics
AI summaryⓘ
The authors created a new system to help self-driving vehicles know their exact location better. They combined sensors on the wheels with special repeating driving paths and a simple neural network to figure out how far the vehicle has moved. Their system uses GPS updates and a smart filtering method to improve accuracy. Tests showed it reduced errors in position by nearly half compared to older methods. This means their approach helps vehicles localize themselves more precisely using fewer sensors.
localizationinertial sensorsneural networkGNSSKalman filterwheel-mounted sensorsnavigationsignal-to-noise ratiodisplacement estimation
Authors
Gal Versano, Itzik Klein
Abstract
Accurate and robust localization remains a fundamental challenge for autonomous ground vehicles. In this work, we propose a hybrid neural inertial navigation framework that integrates a wheel-mounted inertial sensors, enforced periodic trajectories, and a simple, efficient neural network capable of regressing vehicle displacement with GNSS position updates in an error-state extended Kalman filter. The periodic trajectories increase the inertial signal-to-noise ratio, allowing the network to use only inertial readings to estimate displacement. The approach is validated through real-world experiments using multiple wheel-mounted inertial sensors. Experimental results demonstrate that the proposed method achieves a significant improvement in positioning accuracy, reducing the position root mean squared error by approximately 46 % compared to standard wheel-mounted inertial sensor fusion with GNSS updates.