Effective Deployment of CNNs for 3DoF Pose Estimation and Grasping in Industrial Settings

TL;DR

This paper presents a practical system for deploying CNN-based 3-DoF pose estimation and grasping in industrial environments, emphasizing automated data collection and labeling for robust, production-ready solutions.

Contribution

The authors introduce a CNN-based 3-DoF pose estimator with an automated data gathering and labeling procedure tailored for industrial deployment.

Findings

Automated data collection method reduces manual effort.

Robust pose estimation suitable for production environments.

Open source implementation and dataset provided.

Abstract

In this paper we investigate how to effectively deploy deep learning in practical industrial settings, such as robotic grasping applications. When a deep-learning based solution is proposed, usually lacks of any simple method to generate the training data. In the industrial field, where automation is the main goal, not bridging this gap is one of the main reasons why deep learning is not as widespread as it is in the academic world. For this reason, in this work we developed a system composed by a 3-DoF Pose Estimator based on Convolutional Neural Networks (CNNs) and an effective procedure to gather massive amounts of training images in the field with minimal human intervention. By automating the labeling stage, we also obtain very robust systems suitable for production-level usage. An open source implementation of our solution is provided, alongside with the dataset used for the experimental evaluation.