AI-IO: An Aerodynamics-Inspired Real-Time Inertial Odometry for Quadrotors

2026-02-28

AI Summary

This work addresses the limited generalization and accuracy of existing learning-based quadrotor inertial odometry methods, which often lack explicit physical modeling. To overcome this, the study introduces rotor speeds as a key physical quantity and proposes a physically interpretable Transformer architecture that integrates aerodynamic principles with IMU measurement models. A novel temporal modeling approach is designed specifically for aerodynamic noise suppression. Furthermore, the framework incorporates an uncertainty-aware extended Kalman filter (EKF) to enable high-precision, real-time pose estimation. Experimental results demonstrate that the proposed method significantly outperforms state-of-the-art approaches across multiple datasets and real-world systems, achieving a 36.9% improvement in velocity prediction accuracy over baseline methods and an additional 22.4% gain over the current best-performing technique, while maintaining strong generalization and real-time performance.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Inertial Odometry (IO) has gained attention in quadrotor applications due to its sole reliance on inertial measurement units (IMUs), attributed to its lightweight design, low cost, and robust performance across diverse environments. However, most existing learning-based inertial odometry systems for quadrotors either use only IMU data or include additional dynamics-related inputs such as thrust, but still lack a principled formulation of the underlying physical model to be learned. This lack of interpretability hampers the model's ability to generalize and often limits its accuracy. In this work, we approach the inertial odometry learning problem from a different perspective. Inspired by the aerodynamics model and IMU measurement model, we identify the key physical quantity--rotor speed measurements required for inertial odometry and design a transformer-based inertial odometry. By incorporating rotor speed measurements, the proposed model improves velocity prediction accuracy by 36.9%. Furthermore, the transformer architecture more effectively exploits temporal dependencies for denoising and aerodynamics modeling, yielding an additional 22.4% accuracy gain over previous results. To support evaluation, we also provide a real-world quadrotor flight dataset capturing IMU measurements and rotor speed for high-speed motion. Finally, combined with an uncertainty-aware extended Kalman filter (EKF), our framework is validated across multiple datasets and real-time systems, demonstrating superior accuracy, generalization, and real-time performance. We share the code and data to promote further research (https://github.com/SJTU-ViSYS-team/AI-IO).

Problem

• Inertial Odometry
• Quadrotors
• Physical Model
• Generalization
• Accuracy

Innovation

• Inertial Odometry
• Aerodynamics-Inspired Modeling
• Rotor Speed Integration
• Transformer Architecture
• Uncertainty-Aware EKF