触覚表現の事前学習による力ベース動作の少数ショット模倣学習
Few-Shot Learning of Force-Based Motions From Demonstration Through Pre-training of Haptic Representation
触覚表現エンコーダを大量の教師なしデータで事前学習し、動作生成デコーダを少数の人間デモで学習することで、未知のスポンジへの拭き動作を実現する半教師あり模倣学習手法を提案。
著者: Marina Y. Aoyama, João Moura, Namiko Saito, Sethu Vijayakumar
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
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.
