Ground-Optimized 4D Radar-Inertial Odometry via Continuous Velocity Integration using Gaussian Process

2025-02-12

AI Summary

This work addresses the low accuracy and poor robustness of radar-inertial odometry under adverse weather conditions, focusing on two key bottlenecks: inaccurate ground surface modeling and temporal asynchrony between radar and IMU measurements. To tackle these, we propose a region-wise uncertainty-aware ground modeling method—replacing conventional planar fitting—to enhance robustness in complex terrain; and introduce, for the first time, a Gaussian process-based continuous-velocity preintegration framework that tightly fuses 3-DOF radar velocity with IMU measurements to directly yield full 6-DOF motion estimates. Our approach jointly integrates asynchronous temporal alignment, probabilistic uncertainty modeling, and radar point cloud ground segmentation. Evaluated on public benchmarks, it achieves vertical drift <1%, significantly improving elevation accuracy. The implementation is open-sourced.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Motion & Tracking

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Radar ensures robust sensing capabilities in adverse weather conditions, yet challenges remain due to its high inherent noise level. Existing radar odometry has overcome these challenges with strategies such as filtering spurious points, exploiting Doppler velocity, or integrating with inertial measurements. This paper presents two novel improvements beyond the existing radar-inertial odometry: ground-optimized noise filtering and continuous velocity preintegration. Despite the widespread use of ground planes in LiDAR odometry, imprecise ground point distributions of radar measurements cause naive plane fitting to fail. Unlike plane fitting in LiDAR, we introduce a zone-based uncertainty-aware ground modeling specifically designed for radar. Secondly, we note that radar velocity measurements can be better combined with IMU for a more accurate preintegration in radar-inertial odometry. Existing methods often ignore temporal discrepancies between radar and IMU by simplifying the complexities of asynchronous data streams with discretized propagation models. Tackling this issue, we leverage GP and formulate a continuous preintegration method for tightly integrating 3-DOF linear velocity with IMU, facilitating full 6-DOF motion directly from the raw measurements. Our approach demonstrates remarkable performance (less than 1% vertical drift) in public datasets with meticulous conditions, illustrating substantial improvement in elevation accuracy. The code will be released as open source for the community: https://github.com/wooseongY/Go-RIO.

Problem

• Improve radar-inertial odometry accuracy
• Optimize noise filtering for radar
• Integrate continuous velocity with IMU

Innovation

• Zone-based uncertainty-aware ground modeling
• Continuous velocity preintegration using GP
• Tight integration of 3-DOF velocity with IMU