Care3D: An Active 3D Object Detection Dataset of Real Robotic-Care Environments
This provides a dataset for developing assistive robots in health care, addressing a specific data scarcity issue, but it is incremental as it focuses on data collection rather than new methods.
The paper tackles the lack of real-world data for active 3D object detection in robotic health care by introducing an annotated dataset of real environments, including ground truth for SLAM algorithm assessment in one room.
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.