Search papers, labs, and topics across Lattice.
This paper introduces RaDiVe, a novel 4D radar odometry framework that enhances the accuracy and robustness of radar point-cloud registration by addressing the challenges posed by radar's inherent noise and sparsity. The method employs a distance-bounded Normal Distributions Transform (NDT) to optimize correspondence searches and a velocity-discrepancy point uncertainty model to effectively weigh radar points based on their Doppler velocity discrepancies. Evaluations show that RaDiVe significantly outperforms existing baselines, achieving a 44.4% reduction in translational Absolute Trajectory Error and a 21.3% reduction in rotational ATE, all while maintaining real-time performance.
RaDiVe achieves a 44.4% improvement in translational odometry accuracy, setting a new standard for 4D radar applications in challenging environments.
Recent advances in 4D radar enable robust perception in adverse weather; however, the inherent sparsity, noise, and limited positional precision of radar point clouds pose significant challenges for registration-based odometry. In this letter, we propose RaDiVe, a 4D radar odometry framework designed to improve the accuracy and robustness of radar point-cloud registration. We introduce a distance-bounded Normal Distributions Transform (NDT), which improves optimization stability and computational efficiency by restricting the correspondence search to near-distance voxel pairs. To mitigate measurement ambiguity, we propose a velocity-discrepancy point uncertainty model that weights each input 4D radar point according to the discrepancy between its measured Doppler radial velocity and the radial velocity predicted from the estimated ego-velocity. Furthermore, we incorporate Signed Distance Function (SDF)-based surface point extraction via implicit neural mapping to construct a geometrically consistent and noise-filtered local submap. Evaluations across multiple public datasets demonstrate that RaDiVe outperforms existing 4D radar odometry baselines by 44.4% in translational Absolute Trajectory Error (ATE) and 21.3% in rotational ATE on average, while maintaining real-time performance. The source code will be made publicly available to the robotics community: https://github.com/to-be-open-sourced.
