Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation

TL;DR

This paper introduces a simplified and improved training framework for Dense Object Nets that enhances multi-object manipulation capabilities, robustness, and efficiency, reducing data needs and hyperparameter sensitivity.

Contribution

It presents a new training regime with multi-object data, an alternative loss function, and augmentation strategies that outperform previous methods in robustness and accuracy.

Findings

Higher precision in object tracking

Robustness in real-world grasping tasks

Reduced data and hyperparameter sensitivity

Abstract

We propose a framework for robust and efficient training of Dense Object Nets (DON) with a focus on multi-object robot manipulation scenarios. DON is a popular approach to obtain dense, view-invariant object descriptors, which can be used for a multitude of downstream tasks in robot manipulation, such as, pose estimation, state representation for control, etc.. However, the original work focused training on singulated objects, with limited results on instance-specific, multi-object applications. Additionally, a complex data collection pipeline, including 3D reconstruction and mask annotation of each object, is required for training. In this paper, we further improve the efficacy of DON with a simplified data collection and training regime, that consistently yields higher precision and enables robust tracking of keypoints with less data requirements. In particular, we focus on training with multi-object data instead of singulated objects, combined with a well-chosen augmentation scheme. We additionally propose an alternative loss formulation to the original pixelwise formulation that offers better results and is less sensitive to hyperparameters. Finally, we demonstrate the robustness and accuracy of our proposed framework on a real-world robotic grasping task.