Generating Annotated Training Data for 6D Object Pose Estimation in Operational Environments with Minimal User Interaction
This addresses the cost and expertise barriers for deploying pose estimation in operational environments, though it appears incremental as it matches rather than surpasses existing performance.
The paper tackles the problem of expensive annotated training data for 6D object pose estimation in robotics by presenting an autonomous data generation approach that requires minimal user interaction and no expertise, achieving a similar grasping success rate as related work in two experiments.
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.