RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly

TL;DR

This paper introduces RGL-NET, a recurrent graph learning framework that improves autonomous object assembly by modeling inter-part relations and progressive pose updates, achieving higher accuracy and connectivity in shape assembly tasks.

Contribution

The paper presents a novel recurrent graph learning framework for progressive object assembly that outperforms existing methods in accuracy and connectivity on the PartNet dataset.

Findings

Up to 10% improvement in part accuracy.

Up to 15% improvement in connectivity accuracy.

Effective shape recovery from point-cloud components.

Abstract

Autonomous assembly of objects is an essential task in robotics and 3D computer vision. It has been studied extensively in robotics as a problem of motion planning, actuator control and obstacle avoidance. However, the task of developing a generalized framework for assembly robust to structural variants remains relatively unexplored. In this work, we tackle this problem using a recurrent graph learning framework considering inter-part relations and the progressive update of the part pose. Our network can learn more plausible predictions of shape structure by accounting for priorly assembled parts. Compared to the current state-of-the-art, our network yields up to 10% improvement in part accuracy and up to 15% improvement in connectivity accuracy on the PartNet dataset. Moreover, our resulting latent space facilitates exciting applications such as shape recovery from the point-cloud components. We conduct extensive experiments to justify our design choices and demonstrate the effectiveness of the proposed framework.