Learning Cross-Coupled and Regime Dependent Dynamics for Aerial Manipulation

TL;DR

This paper introduces a structured encoder-decoder framework for adaptive residual dynamics learning in aerial manipulators, improving accuracy and real-time adaptation under complex, regime-dependent conditions.

Contribution

It presents a nonlinear latent encoder with a linear decoder enabling online Bayesian adaptation for nonstationary, coupled, and history-dependent dynamics in aerial manipulation.

Findings

Enhanced residual prediction accuracy in experiments

Faster adaptation to changing conditions

Improved trajectory tracking performance with MPC

Abstract

Accurate dynamics models are critical for aerial manipulators operating under complex tasks such as payload transport. However, modeling these systems remains fundamentally challenging due to strong quadrotor-manipulator coupling, delayed aerodynamic interactions, and regime-dependent dynamics variations arising from payload changes and manipulator reconfiguration. These effects produce residual dynamics that are simultaneously cross-coupled, history-dependent, and nonstationary, causing both analytical models and purely offline learned models to degrade during deployment. To address these challenges, we propose a structured encoder-decoder framework for adaptive residual dynamics learning in aerial manipulators. The proposed nonlinear latent encoder captures cross-variable coupling and temporal dependencies from state-input histories, while a lightweight linear latent decoder enables online adaptation under regime-dependent nonstationary dynamics. The linear-in-parameter decoder structure permits closed-form Bayesian adaptation together with consistency-driven covariance inflation, enabling rapid and stable adaptation to both transient and slowly varying dynamics changes while remaining compatible with real-time model predictive control (MPC). Experimental results on a real aerial manipulation platform demonstrate improved residual prediction accuracy, faster adaptation under changing operating conditions, and enhanced MPC-based trajectory tracking performance. These results highlight the importance of jointly modeling coupled temporal dynamics and deployment-time nonstationarity for reliable aerial manipulation.