Efficient Learning of Object Placement with Intra-Category Transfer

TL;DR

This paper introduces a method for robotic object placement that transfers learned arrangements across object categories, enabling efficient training from minimal demonstrations and effective task execution in real-world settings.

Contribution

It proposes a novel intra-category transfer scheme for object arrangements, reducing demonstration requirements and improving task generalization in robotic setting.

Findings

Achieved 73.3% human-evaluated success rate in real robot table setting.

Enabled models to predict object arrangements with as few as five demonstrations.

Demonstrated effective intra-category transfer even with distractors.

Abstract

Efficient learning from demonstration for long-horizon tasks remains an open challenge in robotics. While significant effort has been directed toward learning trajectories, a recent resurgence of object-centric approaches has demonstrated improved sample efficiency, enabling transferable robotic skills. Such approaches model tasks as a sequence of object poses over time. In this work, we propose a scheme for transferring observed object arrangements to novel object instances by learning these arrangements on canonical class frames. We then employ this scheme to enable a simple yet effective approach for training models from as few as five demonstrations to predict arrangements of a wide range of objects including tableware, cutlery, furniture, and desk spaces. We propose a method for optimizing the learned models to enable efficient learning of tasks such as setting a table or tidying up an office with intra-category transfer, even in the presence of distractors. We present extensive experimental results in simulation and on a real robotic system for table setting which, based on human evaluations, scored 73.3% compared to a human baseline. We make the code and trained models publicly available at https://oplict.cs.uni-freiburg.de.