RadarSplat-RIO: Indoor Radar-Inertial Odometry with Gaussian Splatting-Based Radar Bundle Adjustment

2026-04-15

AI Summary

This work addresses the limitations of existing radar SLAM systems, which predominantly rely on frame-to-frame odometry and suffer from cumulative drift due to the absence of multi-frame joint optimization. We present the first radar mapping framework that integrates Gaussian splatting, introducing a Gaussian splatting–based radar bundle adjustment approach that jointly optimizes radar poses and scene geometry by fully exploiting the full-dimensional radar measurements—range, azimuth, and Doppler. Our method establishes the first differentiable, dense scene representation tailored for radar, enabling end-to-end multi-frame joint optimization. Evaluated across multiple indoor environments, the proposed approach significantly improves accuracy, reducing average absolute translational and rotational errors by 90% and 80%, respectively, compared to state-of-the-art radar-inertial odometry methods.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Radar is more resilient to adverse weather and lighting conditions than visual and Lidar simultaneous localization and mapping (SLAM). However, most radar SLAM pipelines still rely heavily on frame-to-frame odometry, which leads to substantial drift. While loop closure can correct long-term errors, it requires revisiting places and relies on robust place recognition. In contrast, visual odometry methods typically leverage bundle adjustment (BA) to jointly optimize poses and map within a local window. However, an equivalent BA formulation for radar has remained largely unexplored. We present the first radar BA framework enabled by Gaussian Splatting (GS), a dense and differentiable scene representation. Our method jointly optimizes radar sensor poses and scene geometry using full range-azimuth-Doppler data, bringing the benefits of multi-frame BA to radar for the first time. When integrated with an existing radar-inertial odometry frontend, our approach significantly reduces pose drift and improves robustness. Across multiple indoor scenes, our radar BA achieves substantial gains over the prior radar-inertial odometry, reducing average absolute translational and rotational errors by 90% and 80%, respectively.

Problem

• radar SLAM
• odometry drift
• bundle adjustment
• pose optimization
• radar-inertial odometry

Innovation

• Radar Bundle Adjustment
• Gaussian Splatting
• Radar-Inertial Odometry
• Multi-frame Optimization
• Range-Azimuth-Doppler Data