Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representation

TL;DR

This paper introduces a semi-supervised learning approach for force-based manipulation tasks that leverages pre-trained haptic representations to enable robots to generalize motions to unseen objects with minimal demonstrations.

Contribution

It proposes a decoupled model with pre-trained haptic encoder and few-shot motion decoder, improving generalization in contact-rich tasks.

Findings

Pre-training enhances recognition of physical properties.

The method outperforms non-pre-trained LfD in unseen object tasks.

Haptic encoder pre-trained in simulation captures real object properties.

Abstract

In many contact-rich tasks, force sensing plays an essential role in adapting the motion to the physical properties of the manipulated object. To enable robots to capture the underlying distribution of object properties necessary for generalising learnt manipulation tasks to unseen objects, existing Learning from Demonstration (LfD) approaches require a large number of costly human demonstrations. Our proposed semi-supervised LfD approach decouples the learnt model into an haptic representation encoder and a motion generation decoder. This enables us to pre-train the first using large amount of unsupervised data, easily accessible, while using few-shot LfD to train the second, leveraging the benefits of learning skills from humans. We validate the approach on the wiping task using sponges with different stiffness and surface friction. Our results demonstrate that pre-training significantly improves the ability of the LfD model to recognise physical properties and generate desired wiping motions for unseen sponges, outperforming the LfD method without pre-training. We validate the motion generated by our semi-supervised LfD model on the physical robot hardware using the KUKA iiwa robot arm. We also validate that the haptic representation encoder, pre-trained in simulation, captures the properties of real objects, explaining its contribution to improving the generalisation of the downstream task.