Good Grasps Only: A data engine for self-supervised fine-tuning of pose estimation using grasp poses for verification

TL;DR

This paper introduces a self-supervised method for robot pose estimation that automatically generates training data through grasp verification, enabling rapid setup and improved accuracy in bin picking tasks.

Contribution

The proposed approach allows for continuous fine-tuning of pose estimation during operation without manual labeling, outperforming existing methods in bin picking scenarios.

Findings

Enhanced pose estimation accuracy across four objects

Outperforms state-of-the-art methods trained on CAD models

Enables rapid, self-supervised system setup

Abstract

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