Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Physics-infused Learning for Aerial Manipulator in Winds and Near-Wall Environments

Yiming Zhang, Junyi Geng

Abstract

Aerial manipulation (AM) expands UAV capabilities beyond passive observation to contact-based operations at high altitudes and in otherwise inaccessible environments. Although recent advances show promise, most AM systems are developed in controlled settings that overlook key aerodynamic effects. Simplified thrust models are often insufficient to capture the nonlinear wind disturbances and proximity-induced flow variations present in real-world environments near infrastructure, while high-fidelity CFD methods remain impractical for real-time use. Learning-based models are computationally efficient at inference, but often struggle to generalize to unseen condition. This paper combines both approaches by integrating a physics-based blade-element model with a learning-based residual force estimator, along with a rotor-speed allocation strategy for disturbance compensation, resulting in a unified control framework. The blade-element model computes per-rotor aerodynamic forces under wind and provides a refined feedforward disturbance estimate. A learning-based estimator then predicts the residual forces not captured by the model, enabling compensation for unmodeled aerodynamic effects. An online adaptation mechanism further updates the residual-force prediction and rotor-speed allocation jointly to reduce the mismatch between desired and realized thrust. We evaluate this framework in both free-flight and wall-contact tracking tasks in a simulated near-wall wind environment. Results demonstrate improved disturbance estimation and trajectory-tracking accuracy over conventional approaches, enabling robust wall-contact execution under challenging aerodynamic conditions.

Physics-infused Learning for Aerial Manipulator in Winds and Near-Wall Environments

Abstract

Aerial manipulation (AM) expands UAV capabilities beyond passive observation to contact-based operations at high altitudes and in otherwise inaccessible environments. Although recent advances show promise, most AM systems are developed in controlled settings that overlook key aerodynamic effects. Simplified thrust models are often insufficient to capture the nonlinear wind disturbances and proximity-induced flow variations present in real-world environments near infrastructure, while high-fidelity CFD methods remain impractical for real-time use. Learning-based models are computationally efficient at inference, but often struggle to generalize to unseen condition. This paper combines both approaches by integrating a physics-based blade-element model with a learning-based residual force estimator, along with a rotor-speed allocation strategy for disturbance compensation, resulting in a unified control framework. The blade-element model computes per-rotor aerodynamic forces under wind and provides a refined feedforward disturbance estimate. A learning-based estimator then predicts the residual forces not captured by the model, enabling compensation for unmodeled aerodynamic effects. An online adaptation mechanism further updates the residual-force prediction and rotor-speed allocation jointly to reduce the mismatch between desired and realized thrust. We evaluate this framework in both free-flight and wall-contact tracking tasks in a simulated near-wall wind environment. Results demonstrate improved disturbance estimation and trajectory-tracking accuracy over conventional approaches, enabling robust wall-contact execution under challenging aerodynamic conditions.
Paper Structure (23 sections, 32 equations, 6 figures, 9 tables, 1 algorithm)

This paper contains 23 sections, 32 equations, 6 figures, 9 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Modeling
  3. Aerial Manipulator Dynamics
  4. Rotor Force and Moment Modeling
  5. Motor Dynamics Modeling
  6. Physics-Infused Learning for Disturbance Compensation
  7. Physics-based Learning of Aerodynamic Parameters
  8. BEMT-based Propeller Rotational Speed Allocation
  9. Physics-infused Residual Learning
  10. Adaptive Residual Disturbance Observer
  11. Simulation Environment Setup
  12. Near-Wall Wind Environment Configuration
  13. Wall-Contact Interaction Setup
  14. Sensor Noise
  15. Task Trajectory
  16. ...and 8 more sections

Figures (6)

  • Figure 1: Rotor thrust and drag characteristics of the APC 8$\times$6 propeller apc8x6 under varying pitch angles $\beta$ at a wind speed of 5 m/s, evaluated across different rotational speeds.
  • Figure 2: Simulated 3D velocity field in the $x$–$y$ plane at $z = 0$ for an oblique freestream wind
  • Figure 3: Noisified IMU acceleration and angular velocity measurements during a steady hover
  • Figure 4: Simulation reference trajectories.
  • Figure 5: Rotor thrust and drag characteristics of the APC 8×6 propeller comparison among simulation groundtruth, parameter-learned BEMT model and zero-wind approximation.
  • ...and 1 more figures