Convolutional Occupancy Models for Dense Packing of Complex, Novel Objects

TL;DR

This paper introduces F-CON, a convolutional shape completion model that improves dense packing of complex objects in cluttered scenes, validated through a new dataset and real-world experiments.

Contribution

The paper presents F-CON, a novel convolutional shape completion model, and COB-3D-v2, a dataset for training and evaluating shape completion in robotics.

Findings

F-CON outperforms existing shape completion methods.

F-CON enables denser packing in cluttered scenes.

The combined approach improves real-world packing efficiency.

Abstract

Dense packing in pick-and-place systems is an important feature in many warehouse and logistics applications. Prior work in this space has largely focused on planning algorithms in simulation, but real-world packing performance is often bottlenecked by the difficulty of perceiving 3D object geometry in highly occluded, partially observed scenes. In this work, we present a fully-convolutional shape completion model, F-CON, which can be easily combined with off-the-shelf planning methods for dense packing in the real world. We also release a simulated dataset, COB-3D-v2, that can be used to train shape completion models for real-word robotics applications, and use it to demonstrate that F-CON outperforms other state-of-the-art shape completion methods. Finally, we equip a real-world pick-and-place system with F-CON, and demonstrate dense packing of complex, unseen objects in cluttered scenes. Across multiple planning methods, F-CON enables substantially better dense packing than other shape completion methods.