Learning-Based Motion Estimation for Autonomous Inspection Robots: Temporally Aligned IMU–RTK Data Fusion

Abstract

This work addresses the problem of increasing the temporal resolution of robot positioning in outdoor inspection tasks by leveraging high-frequency inertial measurements. A learning-based approach is proposed to estimate incremental displacement from IMU data combined with GNSS/RTK positioning, using data collected along a predefined trajectory with a mobile robotic platform. Two neural architectures, LSTM and Transformer, are evaluated under different data preparation strategies. Offline validation shows that variations in hyperparameters have limited impact on performance, while the adopted data representation plays a more significant role, with high-resolution IMU–GNSS alignment outperforming feature-based approaches. The selected models were deployed on the robotic platform and tested in the same environment used for data collection, demonstrating real-time operation at the IMU sampling rate and achieving mean errors of approximately 0.140 m and 0.113 m for LSTM and Transformer, respectively. These results indicate that the proposed approach can enhance positioning update rates and support real-time motion estimation in robotic inspection tasks.