Temporal Learning for End-Effector Position Estimation under Aerodynamic Disturbances in Aerial Continuum Manipulation

2026-09-23

AI Summary

This study addresses the challenge of end-effector positioning for aerial continuum manipulators under UAV-induced aerodynamic disturbances. We propose an aerodynamic residual prediction method that integrates strain-parameterized kinematics with closed-form continuous-time (CfC) networks. By leveraging the continuous-time dynamics of CfC networks, this approach effectively handles time-varying perturbations, overcoming the inherent limitations of conventional static and discrete-time models. Experimental results demonstrate that the proposed CfC-based model reduces the root mean square error (RMSE) to 22.00 mm, achieving improvements of 39.52% and 20.62% over multilayer perceptron (MLP) and gated recurrent unit (GRU) baselines, respectively. These findings indicate a substantial enhancement in positioning accuracy within complex aerodynamic environments.

Abstract

This paper investigates temporal neural networks for \mbox{end-effector} position \mbox{estimation} of an aerial continuum manipulator (ACM) operating under aerodynamic effects induced by the unmanned aerial vehicle (UAV). An experimental dataset is collected under stationary (\mbox{rotor-off}) and \mbox{free-hovering} conditions across continuum robot (CR) configurations and UAV altitudes, providing \mbox{end-effector} position measurements with and without aerodynamic residuals. To establish a nominal framework, \mbox{strain-parameterized} kinematic models with progressively richer strain bases are evaluated to balance model complexity and prediction accuracy. The selected nominal model then serves as the baseline for 3D position residual estimation using a \mbox{closed-form} \mbox{continuous-time} (CfC) neural network, with a multilayer perceptron (MLP) and a gated recurrent unit (GRU) used for comparison. On unseen test experiments, the CfC achieves an RMSE of \(22.00\pm1.70~\mathrm{mm}\) over five random seeds, compared with \(36.38\pm3.58~\mathrm{mm}\) for the MLP and \(27.72\pm2.92~\mathrm{mm}\) for the GRU, corresponding to reductions of \(39.52\%\) and \(20.62\%\), respectively. These results demonstrate the effectiveness of \mbox{continuous-time} learning for \mbox{end-effector} position estimation under aerodynamic disturbances relative to static and \mbox{discrete-time} learning methods.

Problem

• End-effector position estimation
• Aerial continuum manipulator
• Aerodynamic disturbances
• Temporal learning

Innovation

• Continuous-time Neural Network
• Aerial Continuum Manipulator
• End-Effector Position Estimation
• Aerodynamic Disturbances
• Closed-form Continuous-time (CfC)