Care3D: An Active 3D Object Detection Dataset of Real Robotic-Care Environments

TL;DR

Care3D introduces a novel annotated dataset of real robotic-care environments to advance active 3D object detection, addressing the lack of real-world data in health care robotics research.

Contribution

This paper provides the first real-world, annotated dataset for active 3D object detection in robotic health care environments, including ground truth data for SLAM assessment.

Findings

First real-world dataset for active 3D detection in health care robotics

Includes ground truth data for SLAM algorithm evaluation

Addresses data scarcity in robotic health care research

Abstract

As labor shortage increases in the health sector, the demand for assistive robotics grows. However, the needed test data to develop those robots is scarce, especially for the application of active 3D object detection, where no real data exists at all. This short paper counters this by introducing such an annotated dataset of real environments. The captured environments represent areas which are already in use in the field of robotic health care research. We further provide ground truth data within one room, for assessing SLAM algorithms running directly on a health care robot.