Self-RIO: Robust Self-Supervised Odometry Across Diverse Weather and Terrain by Fusing Radar and Inertial Signals

Multi-sensor fusion provides a promising route to robust odometry in GNSS-denied environments. However, existing fusion frameworks often rely on vision or LiDAR as dominant modalities, making their feature representations vulnerable to adverse weather and weak scene structures. To address this, we propose Self-RIO, a self-supervised odometry that integrates 2D millimeter-wave radar and inertial measurement unit (IMU) signals. To the best of our knowledge, this is the first end-to-end self-supervised spinning radar-inertial odometry. Specifically, we design an efficient cross-attention-based multi-modal fusion module that integrates radar and IMU data, facilitating the fusion of more informative features for localization under challenging conditions. Furthermore, to address the sparsity and irregular spatial distribution inherent in radar signals, we introduce a spatial-enhanced sparse CNN-Transformer radar backbone that improves radar feature robustness. Extensive experiments on standard benchmarks confirm the superior robustness of Self-RIO across diverse challenging conditions. On the Oxford Radar RobotCar dataset, Self-RIO achieves up to 22.9% improvement in pose accuracy while reducing computational complexity by 63.1% relative to the existing advanced learning-based method GRAMME, highlighting its robustness under diverse weather and urban conditions. Moreover, consistent improvements on the RADIATE and Oxford Offroad Radar datasets underscore its effectiveness in handling adverse weather and unstructured terrains. Self-RIO also demonstrates strong generalization performance on the MulRan dataset.