Connectionists: See & Grasp: A Visual Haptic Data Set

[Ilker Yildirim]

SEE & GRASP DATA SET

See & Grasp data set is a data set containing visual and haptic features 
for a set of 40 Fribbles. Fribbles are complex, 3-D objects with 
multiple parts and spatial relations among the parts. Moreover, Fribbles 
have a categorical structure---that is, each Fribble is an exemplar from 
a category formed by perturbing a category prototype. The unmodified 3-D 
object files for the whole set of Fribbles can be found on Mike Tarr's 
(Dept. of Psychology at Carnegie Mellon University) web pages. We 
slightly modified these object files so that the connections among parts 
would be stronger. An innovative aspect of our work is that we have 
obtained physical copies of Fribbles fabricated using an extremely 
high-resolution 3-D printing process. The See & Grasp data set is based 
upon this visual and physical copies of Fribbles. We are sharing our 
data set in the hope that it will become a major resource to the 
cognitive science and computer science communities interested in 
perception.

The data set is available at the following web page:

http://www.bcs.rochester.edu/people/robbie/jacobslab/dataset.html

The visual features for each Fribble consist of the pixel values for a 
2-D canonical projection. The data set includes the 3-D computer models 
for each Fribble so that researchers can obtain 2-D projections from 
whichever angle they prefer. The haptic features consist of joint angles 
of a 16 DOF human hand model at the time of a stable grasp simulated by 
the grasping simulator GraspIt! (Miller & Allen, 2004).

Please cite the following paper in relation to the See & Grasp data set.
Yildirim, I. & Jacobs, R. A. (2013). Transfer of object category 
knowledge across visual and haptic modalities: Experimental and 
computational studies. Cognition, 126, 135-148.

Citation for GraspIt!:
Miller, A., & Allen, P. K. (2004). Graspit!: A versatile simulator for 
robotic grasping. IEEE Robotics and Automation Magazine, 11, 110–122.