The RBO Dataset of Articulated Objects and Interactions

TL;DR

The RBO dataset provides comprehensive RGB-D videos, object models, and interaction data for 14 common articulated objects, facilitating research in object manipulation and kinematic understanding.

Contribution

This paper introduces a new dataset with detailed models, annotated interactions, and wrench measurements for articulated objects, supporting advances in manipulation research.

Findings

Contains 358 interaction sequences with ground truth poses

Includes wrench measurements for a subset of interactions

Provides textured 3D models and visualization scripts

Abstract

We present a dataset with models of 14 articulated objects commonly found in human environments and with RGB-D video sequences and wrenches recorded of human interactions with them. The 358 interaction sequences total 67 minutes of human manipulation under varying experimental conditions (type of interaction, lighting, perspective, and background). Each interaction with an object is annotated with the ground truth poses of its rigid parts and the kinematic state obtained by a motion capture system. For a subset of 78 sequences (25 minutes), we also measured the interaction wrenches. The object models contain textured three-dimensional triangle meshes of each link and their motion constraints. We provide Python scripts to download and visualize the data. The data is available at https://tu-rbo.github.io/articulated-objects/ and hosted at https://zenodo.org/record/1036660/.