Good Grasps Only: A data engine for self-supervised fine-tuning of pose estimation using grasp poses for verification
This addresses the need for flexible robotic setups in bin picking, offering an incremental improvement by automating data collection and validation.
The paper tackles the problem of rapid setup for pose estimation in bin picking by introducing a self-supervised fine-tuning method that uses grasp poses for verification, eliminating manual labeling and increasing performance for all tested objects, outperforming a state-of-the-art method trained on CAD models.
In this paper, we present a novel method for self-supervised fine-tuning of pose estimation. Leveraging zero-shot pose estimation, our approach enables the robot to automatically obtain training data without manual labeling. After pose estimation the object is grasped, and in-hand pose estimation is used for data validation. Our pipeline allows the system to fine-tune while the process is running, removing the need for a learning phase. The motivation behind our work lies in the need for rapid setup of pose estimation solutions. Specifically, we address the challenging task of bin picking, which plays a pivotal role in flexible robotic setups. Our method is implemented on a robotics work-cell, and tested with four different objects. For all objects, our method increases the performance and outperforms a state-of-the-art method trained on the CAD model of the objects. Project page available at gogoengine.github.io