Learning Kinematic Descriptions using SPARE: Simulated and Physical ARticulated Extendable dataset

TL;DR

This paper introduces SPARE, a novel extendable dataset of simulated and physical articulated objects, and a deep neural network that accurately predicts kinematic properties, advancing robotic understanding of complex objects.

Contribution

The paper presents the first joint visual and physical dataset for articulated objects and a neural network that outperforms classical methods in kinematic description tasks.

Findings

The neural network accurately predicts the number of links and their lengths.

SPARE dataset enables training and evaluation of articulated object understanding.

Deep learning methods outperform classical tracking approaches.

Abstract

Next generation robots will need to understand intricate and articulated objects as they cooperate in human environments. To do so, these robots will need to move beyond their current abilities--- working with relatively simple objects in a task-indifferent manner--- toward more sophisticated abilities that dynamically estimate the properties of complex, articulated objects. To that end, we make two compelling contributions toward general articulated (physical) object understanding in this paper. First, we introduce a new dataset, SPARE: Simulated and Physical ARticulated Extendable dataset. SPARE is an extendable open-source dataset providing equivalent simulated and physical instances of articulated objects (kinematic chains), providing the greater research community with a training and evaluation tool for methods generating kinematic descriptions of articulated objects. To the best of our knowledge, this is the first joint visual and physical (3D-printable) dataset for the Vision community. Second, we present a deep neural network that can predit the number of links and the length of the links of an articulated object. These new ideas outperform classical approaches to understanding kinematic chains, such tracking-based methods, which fail in the case of occlusion and do not leverage multiple views when available.