Other
OpenRoboCare
Robot caregiving
Expert caregiving demonstrations spanning 15 tasks, with RGB-D views, tactile skin, body poses, gaze and action annotations.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- Other
- Environment
- Indoor
- Data origin
- Real-world
- Sensor count
- 6
- Ground truth
- Available
- Calibration
- Not reported
- Annotations
- Available
Sensor overview
High-level sensor availability before the detailed sensor records below.
Ground truth
Reference scope, method, rate, coverage, and provenance.
| Scope | Method | Reference system | Count | Rate | Coverage |
Reference provenance
|
|---|---|---|---|---|---|---|
| Other | Motion capture | OptiTrack · PrimeX 13 | 12 cameras | Not reported | Partial |
Reference provenance
External
|
|
||||||
| 3D position | Other | Not reported | Not reported | Not reported | Unknown |
Reference provenance
Derived
|
|
||||||
Calibration and synchronization
Reported calibration level, reproducibility signals, and supporting notes.
- Level
- Not reported
- Processed parameters
- Not reported
- Raw calibration data
- Not reported
- Calibration targets
- Not reported
Calibration data
Calibration reproducibility details are not reported.
Notes
Motion capture and eye tracking are calibrated before collection sessions; tactile sensors use ATI force/torque calibration and per-task tare. Three scene cameras are calibrated for triangulation. The paper does not establish which calibration files are released.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
Fully passive manikins represent recipients; active participation is outside collection scope.
Clothing and transfer slings cause optical tracking failures; derived image-based body keypoints have separate provenance.
All demonstrators are female; 19 of 21 are final-year OT students and two are licensed professionals.
Frequent occlusion and caregiving-specific postures challenge general-purpose pose models.
Cameras
scene-rgbd
- Model
- Intel RealSense D435i
- Setup
- Rgbd
- Count
- 3
- Effective cameras
- 6
- Modality
- Rgbd
- Resolution
- Not reported
- Rate
- 15 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Two views face the hospital bed; a third behind the bed faces the wheelchair. Modalities are timestamp-aligned to these RGB-D frames.
IMUs
Not reported
GNSS
Not reported
LiDAR
Not reported
Radar
Not reported
Pitot tube
Not reported
Additional sensors
Other sensor
- Name
- Manikin tactile skin
- Count
- 88
- Notes
- Custom resistive force sensors, 44 on each manikin; 88 across the collection, not a simultaneous single-recipient setup. Native sampling is 60 Hz; synchronized samples are selected at 15 Hz. ATI equipment calibrates voltage to force and skin is tared before each task.
Other sensor
- Name
- Pupil Labs eye-tracking glasses
- Count
- 1
- Notes
- Provides 2D gaze; native eye tracking is 120 Hz, with synchronized samples at 15 Hz. Head pose proxies glasses pose; gaze is low-pass filtered and realigned. First-person video capture is described, but its distributed form needs verification.
Annotations
Reported annotation availability and task support.
- Availability
- Available
- Format
- Not reported
- Class count
- Not reported
Semantic segmentation
Not reported
Instance segmentation
Not reported
Object detection
Not reported
Optical flow
Not reported
Depth ground truth
Not reported
Citation
Citation key and BibTeX kept at the end of the page for reference.
Not reported
Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy