RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assembly
This addresses the challenge of robust assembly in robotics and 3D computer vision, though it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of developing a generalized framework for autonomous part assembly robust to structural variants, using a recurrent graph learning approach that improves part accuracy by up to 10% and connectivity accuracy by up to 15% on the PartNet dataset.
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.