External-Wrench Estimation for Aerial Robots Exploiting a Learned Model

2025-04-10

AI Summary

Existing model-based force observers struggle to distinguish external disturbances (e.g., collisions, wind gusts) from residual dynamics errors (e.g., parametric uncertainties, unmodeled effects), degrading force-feedback control performance. This paper proposes a physics-informed hybrid dynamics framework that explicitly embeds a neural network into a first-principles-based model observer, enabling end-to-end joint learning and suppression of residual dynamics effects for high-fidelity decoupled estimation of external torques. It introduces, for the first time in model-based observers, an interpretable residual learning architecture, where the neural network is co-parameterized and jointly trained with the physical model to optimize overall estimation and control performance. Simulation results demonstrate that, under diverse disturbance scenarios, the proposed method reduces torque estimation error by over 40% compared to pure model-based approaches, significantly enhancing the robustness of force-feedback control.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Low Level & Physics-based Vision
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

This paper presents an external wrench estimator that uses a hybrid dynamics model consisting of a first-principles model and a neural network. This framework addresses one of the limitations of the state-of-the-art model-based wrench observers: the wrench estimation of these observers comprises the external wrench (e.g. collision, physical interaction, wind); in addition to residual wrench (e.g. model parameters uncertainty or unmodeled dynamics). This is a problem if these wrench estimations are to be used as wrench feedback to a force controller, for example. In the proposed framework, a neural network is combined with a first-principles model to estimate the residual dynamics arising from unmodeled dynamics and parameters uncertainties, then, the hybrid trained model is used to estimate the external wrench, leading to a wrench estimation that has smaller contributions from the residual dynamics, and affected more by the external wrench. This method is validated with numerical simulations of an aerial robot in different flying scenarios and different types of residual dynamics, and the statistical analysis of the results shows that the wrench estimation error has improved significantly compared to a model-based wrench observer using only a first-principles model.

Problem

• Estimating external wrench for aerial robots accurately
• Separating residual dynamics from external wrench estimation
• Improving wrench feedback for force controllers

Innovation

• Hybrid model combines neural network and first-principles
• Estimates residual dynamics to isolate external wrench
• Improves wrench estimation accuracy in aerial robots