High-Precision Climbing Robot Localization Using Planar Array UWB/GPS/IMU/Barometer Integration

TL;DR

The paper tackles high-precision localization for climbing robots operating in tall, occluded environments by fusing planar array UWB, GPS, IMU, and barometer data through an Attention Mechanism-based Fusion Algorithm (AMFA). It introduces end-to-end neural networks for planar UWB and barometer solutions and a multimodal attention fusion scheme with adaptive covariance, followed by an Unscented Kalman Filter refinement. Key contributions include the end-to-end UWB and barometer models, the cross-modal attention fusion with reliability gating, and real-world validation showing a fusion RMSE of $0.48\ \mathrm{m}$ and a MAX error of $1.50\ \mathrm{m}$, outperforming GPS/INS-EKF baselines. The approach improves robustness under partial GPS coverage and UWB NLOS, enabling precise task execution and safer coordination for high-altitude robotics.

Abstract

To address the need for high-precision localization of climbing robots in complex high-altitude environments, this paper proposes a multi-sensor fusion system that overcomes the limitations of single-sensor approaches. Firstly, the localization scenarios and the problem model are analyzed. An integrated architecture of Attention Mechanism-based Fusion Algorithm (AMFA) incorporating planar array Ultra-Wideband (UWB), GPS, Inertial Measurement Unit (IMU), and barometer is designed to handle challenges such as GPS occlusion and UWB Non-Line-of-Sight (NLOS) problem. Then, End-to-end neural network inference models for UWB and barometer are developed, along with a multimodal attention mechanism for adaptive data fusion. An Unscented Kalman Filter (UKF) is applied to refine the trajectory, improving accuracy and robustness. Finally, real-world experiments show that the method achieves 0.48 m localization accuracy and lower MAX error of 1.50 m, outperforming baseline algorithms such as GPS/INS-EKF and demonstrating stronger robustness.

Figures (11)

• Figure 1: High-altitude operation robot scenarios. A presents building exterior wall cleaning. B illustrates high-altitude window cleaning. C depicts steel bridge rust removal and painting.
• Figure 2: Localization scenario model for high-altitude climbing robot
• Figure 3: Localization architecture of planar array UWB/GPS/IMU/Barometer Integration
• Figure 4: Localization model of Planar Array UWB
• Figure 5: FCNN Prediction Model for Planar Array UWB Solution