RaDiVe: Robust 4D Radar Odometry with Distance-Bounded NDT and Velocity-Discrepancy Point Uncertainty

2026-07-30

AI Summary

This work addresses the instability in odometry estimation caused by the sparsity, high noise levels, and low positional accuracy inherent in 4D radar point clouds. To this end, we propose a robust 4D radar odometry framework that introduces a range-constrained Normal Distributions Transform (NDT) to enhance registration stability. Our approach innovatively models point cloud uncertainty based on Doppler velocity discrepancies for adaptive weighting and leverages an SDF-driven neural implicit mapping to extract geometrically consistent surface points for constructing local submaps. Evaluated on multiple public datasets, the proposed method achieves an average reduction of 44.4% in translational ATE and 21.3% in rotational ATE compared to state-of-the-art approaches, while maintaining real-time performance.

Abstract

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.

Problem

• 4D radar odometry
• point cloud registration
• sparsity
• noise
• positional precision

Innovation

• 4D radar odometry
• distance-bounded NDT
• velocity-discrepancy uncertainty
• Signed Distance Function
• implicit neural mapping