Fast Payload Calibration for Sensorless Contact Estimation Using Model Pre-training

TL;DR

This paper presents a rapid offline calibration method using pre-trained neural networks to accurately estimate robot dynamics and payloads, enabling efficient sensorless contact detection with minimal online data.

Contribution

It introduces a novel pre-training based calibration scheme that reduces online data needs and improves accuracy in dynamic changes, especially payload variations.

Findings

Achieves online calibration in just 4 seconds.

Effectively estimates payload variations for sensorless contact detection.

Reduces need for extensive online data collection.

Abstract

Force and torque sensing is crucial in robotic manipulation across both collaborative and industrial settings. Traditional methods for dynamics identification enable the detection and control of external forces and torques without the need for costly sensors. However, these approaches show limitations in scenarios where robot dynamics, particularly the end-effector payload, are subject to changes. Moreover, existing calibration techniques face trade-offs between efficiency and accuracy due to concerns over joint space coverage. In this paper, we introduce a calibration scheme that leverages pre-trained Neural Network models to learn calibrated dynamics across a wide range of joint space in advance. This offline learning strategy significantly reduces the need for online data collection, whether for selection of the optimal model or identification of payload features, necessitating merely a 4-second trajectory for online calibration. This method is particularly effective in tasks that require frequent dynamics recalibration for precise contact estimation. We further demonstrate the efficacy of this approach through applications in sensorless joint and task compliance, accounting for payload variability.