Object detection and Autoencoder-based 6D pose estimation for highly cluttered Bin Picking

TL;DR

This paper introduces a framework for 6D pose estimation in cluttered industrial scenes focusing on small objects, primarily using RGB data with depth for refinement, and compares synthetic data generation methods.

Contribution

It presents a novel approach combining RGB-based detection with depth refinement and introduces a pose filtering algorithm for improved accuracy.

Findings

RGB-based detection performs well in cluttered scenes

Synthetic data generation impacts detection accuracy

Pose filtering enhances estimation precision

Abstract

Bin picking is a core problem in industrial environments and robotics, with its main module as 6D pose estimation. However, industrial depth sensors have a lack of accuracy when it comes to small objects. Therefore, we propose a framework for pose estimation in highly cluttered scenes with small objects, which mainly relies on RGB data and makes use of depth information only for pose refinement. In this work, we compare synthetic data generation approaches for object detection and pose estimation and introduce a pose filtering algorithm that determines the most accurate estimated poses. We will make our