Coordinate-Consistent Localization via Continuous-Time Calibration and Fusion of UWB and SLAM Observations

2025-10-07

AI Summary

To address two key bottlenecks in UWB-aided SLAM—frequent origin resets and the requirement for pre-deployed, precisely surveyed UWB anchor positions—this paper proposes a two-stage continuous-time calibration and fusion framework. In Stage I, anchor 3D positions are automatically calibrated from a single dataset by jointly optimizing UWB range measurements, IMU odometry, height priors, and inter-anchor distance constraints. In Stage II, SLAM poses and UWB ranges are tightly coupled within a sliding window to achieve high-accuracy, cross-session coordinate-consistent localization. The framework eliminates the need for repeated calibration, supports temporal synchronization and joint optimization. Evaluated on six drone scenarios from the NTU VIRAL dataset, the method achieves centimeter-level localization accuracy across subsequent sessions using only a single initial calibration. The source code is publicly available.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Onboard simultaneous localization and mapping (SLAM) methods are commonly used to provide accurate localization information for autonomous robots. However, the coordinate origin of SLAM estimate often resets for each run. On the other hand, UWB-based localization with fixed anchors can ensure a consistent coordinate reference across sessions; however, it requires an accurate assignment of the anchor nodes' coordinates. To this end, we propose a two-stage approach that calibrates and fuses UWB data and SLAM data to achieve coordinate-wise consistent and accurate localization in the same environment. In the first stage, we solve a continuous-time batch optimization problem by using the range and odometry data from one full run, incorporating height priors and anchor-to-anchor distance factors to recover the anchors' 3D positions. For the subsequent runs in the second stage, a sliding-window optimization scheme fuses the UWB and SLAM data, which facilitates accurate localization in the same coordinate system. Experiments are carried out on the NTU VIRAL dataset with six scenarios of UAV flight, and we show that calibration using data in one run is sufficient to enable accurate localization in the remaining runs. We release our source code to benefit the community at https://github.com/ntdathp/slam-uwb-calibration.

Problem

• Achieving coordinate-consistent robot localization across multiple sessions
• Calibrating UWB anchor positions using continuous-time batch optimization
• Fusing UWB and SLAM data for accurate positioning in unified coordinates

Innovation

• Continuous-time batch optimization for anchor calibration
• Sliding-window fusion of UWB and SLAM data
• Two-stage approach achieving coordinate-consistent localization