Handheld
Waterloo 40K naturalistic grasp demonstrations
Robotic grasp demonstration and grasp planning
Roughly 40,000 successful human-controlled ReFlex gripper grasps on 109 rigid objects, with pre-grasp RGB/depth images, 6DOF trajectories and finger positions.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- Handheld
- Environment
- Not reported
- Data origin
- Real-world
- Sensor count
- 4
- 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
|
|---|---|---|---|---|---|---|
| 6DoF | Motion capture | Northern Digital Inc. · Polaris | Not reported | Not reported | Full |
Reference provenance
External
|
|
||||||
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
Each trial saves home finger servo positions. Home alignment is performed visually and repeated after mechanical repairs. Tool-to-gripper transforms are measured using a temporarily mounted reference tool; camera calibration release is not established.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
Failed grasps are excluded, so the collection does not provide failed examples.
Rigid-object collection excludes unsuitable-size and non-rigid YCB objects; 48 of the 109 objects are from YCB.
Use, sharing and modification are described as free for non-commercial purposes.
Gripper flexion is jointly commanded by the joystick rather than independently controlled for each finger.
Cameras
realsense-sr300
- Model
- RealSense SR300
- Setup
- Rgbd
- Count
- 1
- Effective cameras
- 2
- Modality
- Rgbd
- Resolution
- Not reported
- Rate
- Not reported
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Pre-grasp RGB and depth images; camera activation alternates with the infrared motion tracker. Fixed to the table frame.
zed
- Model
- Stereolabs ZED
- Setup
- Stereo
- Count
- 1
- Effective cameras
- 2
- Modality
- Rgb
- Resolution
- Not reported
- Rate
- Not reported
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Pre-grasp stereo RGB images and depth maps estimated with ZED software; fixed to the table frame. No continuous image rate is established.
IMUs
Not reported
GNSS
Not reported
LiDAR
Not reported
Radar
Not reported
Pitot tube
Not reported
Additional sensors
Not reported
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.
@misc{iyengar2018grasps,
title={A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations},
author={Iyengar, Rajan and Reyes Osorio, Victor and Bhattachan, Presish and Ragobar, Adrian and Tripp, Bryan},
year={2018},
eprint={1812.11683},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/1812.11683v1}
}
Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy