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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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 semisupervised LfD approach decouples the learnt model into a haptic representation encoder and a motion generation decoder. This enables us to pre-train the first using a 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.
Original languageEnglish
Title of host publication2024 IEEE International Conference on Robotics and Automation (ICRA)
PublisherIEEE
Pages1-7
Number of pages7
Publication statusAccepted/In press - 31 Jan 2024
Event2024 IEEE International Conference on Robotics and Automation - Yokohama, Japan
Duration: 13 May 202417 May 2024
https://2024.ieee-icra.org/

Conference

Conference2024 IEEE International Conference on Robotics and Automation
Abbreviated titleICRA 2024
Country/TerritoryJapan
CityYokohama
Period13/05/2417/05/24
Internet address

Fingerprint

Dive into the research topics of 'Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representation'. Together they form a unique fingerprint.

Cite this