HDVIO2.0: Wind and Disturbance Estimation with Hybrid Dynamics VIO

2025-04-01

AI Summary

To address the degradation of visual-inertial odometry (VIO) performance in micro air vehicles under external disturbances (e.g., wind gusts), low fidelity of conventional rigid-body dynamics models, and challenges in online integration of full rotational dynamics, this paper proposes HDVIO2.0—the first continuous-time, tightly coupled 6-DOF VIO framework incorporating complete rotational dynamics. Its core innovations include: (1) a hybrid dynamics model fusing point-mass kinematics with a data-driven learning module; (2) joint estimation of vehicle states and external wrenches via motion prediction residuals; and (3) a learned compensation mechanism driven by control commands and historical IMU measurements. The method ensures real-time operation while delivering high-accuracy, robust state estimation. Evaluated on public and proprietary UAV datasets, as well as real-world wind-field experiments (≤25 km/h), HDVIO2.0 significantly outperforms state-of-the-art methods—achieving precise dynamics prediction without requiring full-state priors.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Low Level & Physics-based Vision
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Visual-inertial odometry (VIO) is widely used for state estimation in autonomous micro aerial vehicles using onboard sensors. Current methods improve VIO by incorporating a model of the translational vehicle dynamics, yet their performance degrades when faced with low-accuracy vehicle models or continuous external disturbances, like wind. Additionally, incorporating rotational dynamics in these models is computationally intractable when they are deployed in online applications, e.g., in a closed-loop control system. We present HDVIO2.0, which models full 6-DoF, translational and rotational, vehicle dynamics and tightly incorporates them into a VIO with minimal impact on the runtime. HDVIO2.0 builds upon the previous work, HDVIO, and addresses these challenges through a hybrid dynamics model combining a point-mass vehicle model with a learning-based component, with access to control commands and IMU history, to capture complex aerodynamic effects. The key idea behind modeling the rotational dynamics is to represent them with continuous-time functions. HDVIO2.0 leverages the divergence between the actual motion and the predicted motion from the hybrid dynamics model to estimate external forces as well as the robot state. Our system surpasses the performance of state-of-the-art methods in experiments using public and new drone dynamics datasets, as well as real-world flights in winds up to 25 km/h. Unlike existing approaches, we also show that accurate vehicle dynamics predictions are achievable without precise knowledge of the full vehicle state.

Problem

• Estimates wind and disturbances in VIO systems
• Models 6-DoF dynamics with minimal runtime impact
• Improves accuracy without full vehicle state knowledge

Innovation

• Hybrid dynamics model combining point-mass and learning
• Continuous-time functions for rotational dynamics
• Divergence-based estimation of external forces