# 6DoF assembly pose estimation dataset for robotic manipulation

## TL;DR

This paper introduces a new dataset for robotic assembly tasks, providing RGB-D images, 3D meshes, and assembly poses to improve perception models.

## Contribution

The paper presents a novel dataset with assembly poses and 3D meshes in canonical frames for robotic manipulation.

## Key findings

- The dataset includes two simulated assembly scenes with RGB-D images and ground truth assembly poses.
- It extends the BOP format to support better training of perception models for robotic assembly tasks.

## Abstract

Robotic assembling is a challenging task that requires cognition and dexterity. In recent years, perception tools have achieved tremendous success in endowing the cognitive capabilities to robots. Although these tools have succeeded in tasks such as detection, scene segmentation, pose estimation and grasp manipulation, the associated datasets and the dataset contents lack crucial information that requires adapting them for assembling pose estimation. Furthermore, existing datasets of object 3D meshes and point clouds are presented in non-canonical view frames and therefore lack information to train perception models that infer on a visual scene. The dataset presents 2 simulated object assembly scenes with RGB-D images, 3D mesh files and ground truth assembly poses as an extension for the State-of-the-Art BOP format. This enables smooth expansion of existing perception models in computer vision as well as development of novel algorithms for estimating assembly pose in robotic assembly manipulation tasks.