Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction

TL;DR

This paper introduces an autonomous method for generating annotated training data for 6D object pose estimation, reducing the need for expert input and addressing the domain gap between synthetic and real data.

Contribution

It presents a novel, minimally interactive approach to automatically generate training data for 6D pose estimation in real operational environments.

Findings

Achieved similar grasping success rates with autonomous data as with non-autonomous datasets.

Reduced user interaction and expertise needed for data generation.

Demonstrated effectiveness in two grasping experiments.

Abstract

Recently developed deep neural networks achieved state-of-the-art results in the subject of 6D object pose estimation for robot manipulation. However, those supervised deep learning methods require expensive annotated training data. Current methods for reducing those costs frequently use synthetic data from simulations, but rely on expert knowledge and suffer from the "domain gap" when shifting to the real world. Here, we present a proof of concept for a novel approach of autonomously generating annotated training data for 6D object pose estimation. This approach is designed for learning new objects in operational environments while requiring little interaction and no expertise on the part of the user. We evaluate our autonomous data generation approach in two grasping experiments, where we archive a similar grasping success rate as related work on a non autonomously generated data set.