RobustLIVO: Robust LiDAR, Visual and IMU Odometry with Sliding Filtering and Compensation

In environments characterized by low texture or sparse LiDAR returns, conventional LiDAR-IMU fusion systems are prone to drift and significant loss of accuracy over time. To address these limitations, we propose a robust, lightweight, and efficient multi-sensor localization framework that tightly integrates a sliding-window filtering approach with vision-based incremental motion compensation. This design enables real-time correction of both translational and rotational errors without the need for computationally expensive global optimization. The system also retains full compatibility with multi-agent collaborative localization frameworks, enhancing scalability. Additionally, we introduce an exponentially weighted moving average (EMA)-based IMU filter and a visual motion estimation pipeline that leverages ORB feature matching and essential matrix decomposition for robust relative pose estimation. Experimental validation conducted on a high-precision, synchronized motion capture platform shows a root mean square positioning error of only 0.0710 m. These results confirm the effectiveness of the proposed method in challenging scenarios with degraded visual or geometric features. The approach is well-suited for real-time deployment in autonomous, GPS-denied, and dynamic multi-robot environments.