AirIO: Learning Inertial Odometry with Enhanced IMU Feature Observability

2025-01-26

AI Summary

To address information loss and degraded accuracy in existing motion tracking methods under high-dynamic, nonlinear UAV flight—caused by sensor processing limitations—this paper proposes a pure IMU-based inertial odometry system. Methodologically, it introduces three key innovations: (1) the first formal analysis revealing that global coordinate transformations impair motion observability; (2) a dual-mechanism design combining body-frame modeling and explicit attitude encoding to enhance IMU feature discriminability and generalizability; and (3) an integrated framework fusing a data-driven AirIMU error compensation module with an uncertainty-aware extended Kalman filter (EKF). Evaluated on three UAV datasets, the system achieves a 66.7% average improvement in pose accuracy over baselines; incorporating attitude encoding yields an additional 23.8% gain. Crucially, it demonstrates strong generalization to unseen aggressive maneuvers and maintains real-time robustness.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Inertial odometry (IO) using only Inertial Measurement Units (IMUs) offers a lightweight and cost-effective solution for Unmanned Aerial Vehicle (UAV) applications, yet existing learning-based IO models often fail to generalize to UAVs due to the highly dynamic and non-linear-flight patterns that differ from pedestrian motion. In this work, we identify that the conventional practice of transforming raw IMU data to global coordinates undermines the observability of critical kinematic information in UAVs. By preserving the body-frame representation, our method achieves substantial performance improvements, with a 66.7% average increase in accuracy across three datasets. Furthermore, explicitly encoding attitude information into the motion network results in an additional 23.8% improvement over prior results. Combined with a data-driven IMU correction model (AirIMU) and an uncertainty-aware Extended Kalman Filter (EKF), our approach ensures robust state estimation under aggressive UAV maneuvers without relying on external sensors or control inputs. Notably, our method also demonstrates strong generalizability to unseen data not included in the training set, underscoring its potential for real-world UAV applications.

Problem

• Motion Tracking
• Drone Flight
• Sensor Data Processing

Innovation

• AirIO
• AirIMU
• Extended Kalman Filter