Human Grasping datasets

The measurement was performed at LMU in Munich at the Lab of Heiner Deubel in collaboration with Javier Romero (libicocco[at]gmail.com) from KTH, Stockholm, Sweden.

The setup was the following:

The average hand length and width were 185.2mm and 81.1mm respectively, with standard deviations 13.3mm and 7.4mm. A Polhemus Liberty system with six magnetic sensors was used for recording the data. The spatial and angular resolution of each sensor is 0.8 mm and 0.15 degrees respectively. A sensor was applied to each fingertip, positioned on the fingernail and one was placed on the dorsum of the hand. See left Figure below for how the markers were applied to the hand. The subjects were asked to perform the 31 different grasp types as described in the taxonomy section on an object typical for the specific grasp. The grasps "Distal Type" and "Tripod Variation" were omitted due to their very special nature. An updated grasp list can be found here. They were shown a picture of each grasp and a demonstration of the grasp was performed if the subject had problems mimicking the grasp on the picture to start with. Initially, the hand was placed in front of the table in a flat hand posture. Upon a starting signal, the subject grasped an object with the desired grasp type, lifted the object (this moment is shown in the right Figure below), put it down again and retreated the hand to the starting position. The data recording started when the hand began to move and ended when the hand was returned to the initial position. Each grasp type was performed twice, the first one was used to create the test set and the second one the training set. To eliminate the global hand movements, the fingertip sensors were transformed into the wrist coordinate system.

Sensors applied to the hand
Actual grasp posture

The recorded movements are stored in a matrix, where different versions can be downloaded below. The size of the matrix is 5 subjects x 2 trials x 31 grasp types x N samples x D dimensions.

Datasets with rotation matrices

The dimension D of the dataset is 60 (5x12) and they are distributed as following.


Additionally the raw data is provided, which is not tranformed into the wrist coordinate system. Therefore the global movement of the hand is still present in the data. As in that case there is an additional sensor (the wrist sensor) the dimensions D increase by 12. The data of the wrist is in between the thumb and the middle finger. That means that the ordering of the fingers in the raw data is: Index - Thumb - Wrist (the reference sensor) - Middle - Ring - Little.
Downloads:
N = 30, D = 60 (.mat, 4 mb)
N = 30, D = 72 (raw data) (.mat, 4 mb)

N = 100, D = 60 (.mat, 13.8 mb)
N = 100, D = 72 (raw data) (.mat, 14 mb)

N = 600, D = 60 (.mat, 83 mb)
N = 600, D = 72 (raw data) (.mat, 87 mb)


Datasets with quaternions

The dimension D of the dataset is 35 (5x7) and they are distributed as following.


Again the raw data is also provided. This increases the dimension D to 42. The ordering of the sensors is the following: Index - Thumb - Wrist - Middle - Ring - Little.
Downloads:
N = 30, D = 35 (.mat, 2.5 mb)
N = 30, D = 42 (raw data) (.mat, 1.6 mb)

N = 100, D = 35 (.mat, 8 mb)
N = 100, D = 42 (raw data) (.mat, 5 mb)

N = 600, D = 35 (.mat, 48 mb)
N = 600, D = 42 (raw data) (.mat, 32 mb)

Description of the grasped objects

  1. Large Diameter: Cylinder 11cm dia
  2. Small Diameter: Cylinder 3cm dia
  3. Medium Wrap: Cylinder 3cm dia
  4. Adducted Thumb: Cylinder 3cm dia
  5. Light Tool: Cylinder 1cm dia
  6. Prismatic 4 Finger: Cylinder 1cm dia
  7. Prismatic 3 Finger: Cylinder 1cm dia
  8. Prismatic 2 Finger: Cylinder 1cm dia
  9. Palmar Pinch: Coin
  10. Power Disk: flat cylinder, 8cm dia 2mm high, mini CD
  11. Power Sphere: Tennis Ball (sphere 67mm dia)
  12. Precision Disk: CD
  13. Precision Sphere: Tennis Ball
  14. Tripod: Golf Ball (sphere 43mm dia)
  15. Fixed Hook: cylinder 3cm dia
  16. Lateral: Credit Card
  17. Index Finger Extension: Cylinder 3cm dia
  18. Extension Type: Plate
  19. Writing Tripod: Cylinder 1cm dia
  20. Parallel Extension: Box,4 cm thick
  21. Adduction Grip: Cylinder, 1cm dia
  22. Tip Pinch: 5mm Cube
  23. Lateral Tripod: Bottle Cap
  24. Sphere 4 Finger: Tennis Ball
  25. Quadpod: Golf Ball
  26. Sphere 3 Finger: Tennis Ball
  27. Stick: Cylinder 1cm dia
  28. Palmar: Plate
  29. Ring: Cylinder, 64mm dia
  30. Vental: Cylinder 1cm dia
  31. Inferior Pincer: Golf ball (sphere 43mm dia)



For citation of the Toolbox please use the following, depending on which fits better:

J. Romero, T. Feix, H. Kjellström, and D. Kragic,
"Spatio-temporal modeling of grasping actions,"
2010 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, October 2010, pp. 2103-2108.
[Online]. Available: http://grasp.xief.net
bib

----OR----

T. Feix, J. Romero, C. H. Ek, H.-B. Schmiedmayer, and D. Kragic,
"A metric for Comparing the Anthropomorphic Motion Capability of Artificial Hands,"
Robotics, IEEE Transactions on, vol. 29, no. 1, pp. 82-93, Feb. 2013.
[Online]. Available: http://grasp.xief.net
bib, pdf, IEEE