Dataset Name: UNIPI Dataset (October 2011)
Hand Type: Human Hand
Research Groups: UNIPI
Data Type: Human Postures
Data Structure: Joint Angles (deg)
Data Format: .mat
Sampling Rate: >100 Hz (480 Hz)
Action Type: Static Grasps
Objects Type: Imagined Objects
Kin. Model # DoFs: <= 15 (15) Equipment: Motion Capture System -> Phase Space
# of Actions/Hand Configurations: >20 (57)
# of Subjects: 1
An optical motion capture system (Phase Space, San Leandro, CA – USA) with 19 active markers was used to collect a large number of static grasp positions. Subject AT(M,26) performed all the grasps of 57 imagined objects described in . These data were acquired twice to define a set of 114 data. Data collection was approved by the University of Pisa Institutional Review Board. The dataset consists of a Matlab data matrix X, where each row describes the posture – using the above mentioned 15 DoFs kinematic model – corresponding to the grasping of the imagined objects. More information can be found on the report that accompanies the dataset.
How to Cite:
 M. Bianchi, P. Salaris, and A. Bicchi. Synergy-based hand pose sensing: Reconstruction enhancement. International Journal of Robotics Research. 32(4):396-406, 2013.
 M. Bianchi, P. Salaris, and A. Bicchi. Synergy-based hand pose Sensing: Optimal glove design. International Journal of Robotics Research. 32(4):407-424, 2013.