Uncertainty-Aware Velocity Correction for Proprioceptive Vehicle Localization using Evidential Mamba
For intelligent vehicles requiring reliable localization without external infrastructure, this work provides a practical, low-cost alternative to dedicated velocity sensors.
The paper proposes EVC-Mamba, a learning-based architecture that uses a Mamba state space model and evidential deep learning to estimate velocity from onboard sensors for IMU drift correction in GNSS-denied environments. It achieves localization accuracy within 10% of a dedicated external velocity sensor and runs at 40 Hz on edge hardware.
Reliable localization in GNSS-denied environments remains a fundamental challenge for intelligent vehicles, as inertial navigation systems accumulate unbounded drift without external correction. Existing approaches provide drift correction through dedicated infrastructure, expensive external sensors, or complex multi-sensor fusion, each introducing practical deployment barriers. We propose Evidential Velocity Correction using Mamba (EVC-Mamba), a learning-based architecture that transforms onboard vehicle sensor data into a virtual velocity sensor for IMU drift correction without additional hardware. A Mamba-based selective state space model captures the temporal dynamics of vehicle motion, while evidential deep learning with a Normal-Inverse-Gamma distribution provides principled uncertainty quantification. The resulting uncertainty-aware velocity estimate is incorporated as a virtual correction measurement into an Error-State Extended Kalman Filter to reduce position drift. Evaluation on real-world vehicle data demonstrates that inertial navigation using the proposed velocity correction achieves localization accuracy within 10% of a dedicated external velocity sensor across different outage durations. The proposed architecture supports real-time onboard deployment at 40 Hz on edge hardware, enabling reliable localization during prolonged GNSS outages.