AERMANI-Diffusion: Regime-Conditioned Diffusion for Dynamics Learning in Aerial Manipulators

TL;DR

This paper introduces AERMANI-Diffusion, a regime-conditioned diffusion model that captures the complex, nonlinear residual forces in aerial manipulators, improving control accuracy across diverse operating conditions.

Contribution

It presents a novel diffusion-based framework with a temporal encoder for modeling residual dynamics conditioned on regime changes, enhancing robustness and accuracy in aerial manipulator control.

Findings

Significantly improves tracking accuracy in real-world tests.

Effectively models diverse residual forces across regimes.

Enables adaptive control with uncertainty compensation.

Abstract

Aerial manipulators undergo rapid, configuration-dependent changes in inertial coupling forces and aerodynamic forces, making accurate dynamics modeling a core challenge for reliable control. Analytical models lose fidelity under these nonlinear and nonstationary effects, while standard data-driven methods such as deep neural networks and Gaussian processes cannot represent the diverse residual behaviors that arise across different operating conditions. We propose a regime-conditioned diffusion framework that models the full distribution of residual forces using a conditional diffusion process and a lightweight temporal encoder. The encoder extracts a compact summary of recent motion and configuration, enabling consistent residual predictions even through abrupt transitions or unseen payloads. When combined with an adaptive controller, the framework enables dynamics uncertainty compensation and yields markedly improved tracking accuracy in real-world tests.