Dr-BA: Separable Optimization for Direct Radar Bundle Adjustment & Localization

• URL: http://arxiv.org/abs/2605.07041v1
• Date: Thu, 07 May 2026 23:41:16 GMT
• Title: Dr-BA: Separable Optimization for Direct Radar Bundle Adjustment & Localization
• Abstract summary: Dr-BA is a first-of-its-kind radar bundle adjustment framework that operates directly on 2D spinning radar intensity images.<n>Dr-BA achieves state-of-the-art radar-based BA and cross-session localization performance, demonstrated on more than 200 km of on-road data.
• Score: 12.318856176227383
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper introduces Dr-BA, a first-of-its-kind radar bundle adjustment (BA) framework that operates directly on 2D spinning radar intensity images. Unlike camera or lidar sensors, radar is largely unaffected by precipitation, making it a critical modality for autonomous systems that require all-weather robustness. Existing state estimation approaches using spinning radar typically extract sparse point clouds from range-azimuth-intensity measurements and apply point cloud alignment techniques to estimate vehicle motion, scene structure, or to localize within an existing map. In contrast, Dr-BA uses the full radar returns from multiple scans to jointly estimate dense maps and sensor poses. By formulating the problem as a separable optimization, we derive an efficient and general solution that decouples pose estimation from mapping. In addition to solving the BA problem, this formulation naturally extends to direct radar-only localization (DRL) within a previously built map. Dr-BA achieves state-of-the-art radar-based BA and cross-session localization performance, demonstrated on more than 200 km of on-road data across five distinct routes. Our implementation is publicly available at https://github.com/utiasASRL/dr_ba.

Related papers

• DiffRadar: Differentiable Physics-Aware Radar SLAM with Gaussian Fields [8.442884076695789]
  We present DiffRadar, a real-time radar SLAM system that models radar observations as a differentiable, physics-aware Gaussian field.<n>DiffRadar represents the scene as anisotropic Gaussian primitives and renders radar measurements in range-azimuth and Doppler-azimuth spaces.<n>We implement DiffRadar on commodity FMCW radar hardware and evaluate it on both the public Radarize benchmark and a controlled stress-test suite.
  arXiv  Detail & Related papers  (2026-07-14T02:08:14Z)
• RadarSim: Simulating Single-Chip Radar via Multimodal Neural Fields [49.41438378775056]
  Radars are an ideal complement to cameras, with cameras offering fine angular resolution and radars providing metric depth and robustness under adverse weather.<n>RadarSim produces sharper geometry and Doppler range frames than radar-only reconstructions.
  arXiv  Detail & Related papers  (2026-05-25T21:03:40Z)
• Dr-PoGO: Direct Radar Pose-Graph Optimization [11.790199751127574]
  This paper introduces Dr-PoGO, a method for Simultaneous Localization And Mapping (SLAM) using a 2D spinning radar.<n>Unlike cameras or lidars that require line-of-sight, millimetre-wave radars can see' through dust, falling snow, rain, etc.<n>Dr-PoGO demonstrates state-of-the-art performance over 300km of data in various real-world automotive environments.
  arXiv  Detail & Related papers  (2026-05-06T11:58:39Z)
• RadarSplat-RIO: Indoor Radar-Inertial Odometry with Gaussian Splatting-Based Radar Bundle Adjustment [15.74169173366249]
  Radar is more resilient to adverse weather and lighting conditions than visual and Lidar simultaneous localization and mapping (SLAM)<n>Most radar SLAM pipelines still rely heavily on frame-to-frame odometry, which leads to substantial drift.<n>We present the first radar bundle adjustment (BA) framework enabled by Gaussian Splatting (GS), a dense and differentiable representation.
  arXiv  Detail & Related papers  (2026-04-15T05:26:46Z)
• RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving [14.25906590501402]
  Radar-to-LiDAR place recognition can localize radar scans within existing LiDAR maps.<n>We propose RLPR, a robust radar-to-LiDAR place recognition framework compatible with single-chip, scanning, and 4D radars.<n>Experiments on four datasets demonstrate that RLPR achieves recognition accuracy with strong zero-shot generalization capabilities.
  arXiv  Detail & Related papers  (2026-03-09T03:28:44Z)
• RadarGen: Automotive Radar Point Cloud Generation from Cameras [64.69976771710057]
  We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery.<n>RadarGen adapts efficient image-latent diffusion to the radar domain by representing radar measurements in bird's-eye-view form.<n>We show that RadarGen captures characteristic radar measurement distributions and reduces the gap to perception models trained on real data.
  arXiv  Detail & Related papers  (2025-12-19T18:57:33Z)
• Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar [62.51065633674272]
  We introduce Radar Fields - a neural scene reconstruction method designed for active radar imagers. Our approach unites an explicit, physics-informed sensor model with an implicit neural geometry and reflectance model to directly synthesize raw radar measurements. We validate the effectiveness of the method across diverse outdoor scenarios, including urban scenes with dense vehicles and infrastructure.
  arXiv  Detail & Related papers  (2024-05-07T20:44:48Z)
• Pointing the Way: Refining Radar-Lidar Localization Using Learned ICP Weights [10.613476233222347]
  We build on ICP-based radar-lidar localization by including a learned preprocessing step that weights radar points based on high-level scan information.<n>To train the weight-generating network, we present a novel, stand-alone, open-source differentiable ICP library.
  arXiv  Detail & Related papers  (2023-09-15T19:37:58Z)
• Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion [74.84019379368807]
  We propose a novel method named EchoFusion to skip the existing radar signal processing pipeline. Specifically, we first generate the Bird's Eye View (BEV) queries and then take corresponding spectrum features from radar to fuse with other sensors.
  arXiv  Detail & Related papers  (2023-07-31T09:53:50Z)
• LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion [52.59664614744447]
  We present LiRaNet, a novel end-to-end trajectory prediction method which utilizes radar sensor information along with widely used lidar and high definition (HD) maps. automotive radar provides rich, complementary information, allowing for longer range vehicle detection as well as instantaneous velocity measurements.
  arXiv  Detail & Related papers  (2020-10-02T00:13:00Z)
• RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model [14.155337185792279]
  We propose an end-to-end deep learning framework for Radar Localization on Lidar Map (RaLL) RaLL exploits the mature lidar mapping technique, thus reducing the cost of radar mapping. Our proposed system achieves superior performance over $90km$ driving, even in generalization scenarios where the model training is in UK.
  arXiv  Detail & Related papers  (2020-09-15T13:13:38Z)
• RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects [73.80316195652493]
  We tackle the problem of exploiting Radar for perception in the context of self-driving cars. We propose a new solution that exploits both LiDAR and Radar sensors for perception. Our approach, dubbed RadarNet, features a voxel-based early fusion and an attention-based late fusion.
  arXiv  Detail & Related papers  (2020-07-28T17:15:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.