Frequency-aware Decomposition Learning for Sensorless Wrench Forecasting on a Vibration-rich Hydraulic Manipulator

TL;DR

This paper introduces a frequency-aware neural network for sensorless high-frequency wrench forecasting on vibration-rich hydraulic manipulators, leveraging spectral decomposition and transfer learning.

Contribution

The proposed Frequency-aware Decomposition Network (FDN) effectively predicts high-frequency vibrations and wrench in robotic tasks, utilizing spectral filtering and transfer learning from large datasets.

Findings

FDN outperforms baseline estimators in high-frequency wrench prediction.

Transfer learning improves estimation accuracy across frequency bands.

FDN effectively models spectral residuals with probabilistic heads.

Abstract

Force and torque (F/T) sensing is critical for robot-environment interaction, but physical F/T sensors impose constraints in size, cost, and fragility. To mitigate this, recent studies have estimated force/wrench sensorlessly from robot internal states. While existing methods generally target relatively slow interactions, tasks involving rapid interactions, such as grinding, can induce task-critical high-frequency vibrations, and estimation in such robotic settings remains underexplored. To address this gap, we propose a Frequency-aware Decomposition Network (FDN) for short-term forecasting of vibration-rich wrench from proprioceptive history. FDN predicts spectrally decomposed wrench with asymmetric deterministic and probabilistic heads, modeling the high-frequency residual as a learned conditional distribution. It further incorporates frequency-awareness to adaptively enhance input spectra with learned filtering and impose a frequency-band prior on the outputs. We pretrain FDN on a large-scale open-source robot dataset and transfer the learned proprioception-to-wrench representation to the downstream. On real-world grinding excavation data from a 6-DoF hydraulic manipulator and under a delayed estimation setting, FDN outperforms baseline estimators and forecasters in the high-frequency band and remains competitive in the low-frequency band. Transfer learning provides additional gains, suggesting the potential of large-scale pretraining and transfer learning for robotic wrench estimation. Code and data will be made available upon acceptance.