Other
HABIT
Human-aware robot manipulation
Human-present bimanual manipulation demonstrations across 60 tasks, with five RGB views, robot kinematics and human/robot subtask annotations.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- Other
- Environment
- Not reported
- Data origin
- Real-world
- Sensor count
- 5
- Ground truth
- Not reported
- 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.
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
Not reportedKnown or intentional limitations
Reported constraints and characteristics to check before using the dataset.
Single recording environment, ten human operators and one-to-one human-robot interaction.
Public participant faces are blurred; no audio is collected.
Participant withdrawal may remove episodes from author-controlled releases.
Cameras
rgb-views
- Model
- Not reported
- Setup
- Mono
- Count
- 5
- Effective cameras
- 5
- Modality
- Rgb
- Resolution
- 640 x 480
- Rate
- 10 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Two wrist views, robot egocentric, human head-mounted and exocentric views. All five are released; evaluated policies use only the three robot-side views. Wrist FoV 125 degrees and center FoV 100 degrees, with axis unspecified.
IMUs
GNSS
LiDAR
Radar
Pitot tube
Additional sensors
Annotations
Reported annotation availability and task support.
- Availability
- Available
- Format
- Not reported
- Class count
- Not reported
Citation
Citation key and BibTeX kept at the end of the page for reference.
@article{song2026habit,
title={HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation},
author={Song, Jaehwi and Jeong, Suchae and Jeon, Byeongguk and Kim, Sungdong and Seo, Minjoon and Son, Hyungmok and Lee, Kimin},
journal={arXiv preprint arXiv:2606.31682},
year={2026}
}
Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy