Published:
2014-11-05
Proceedings:
Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 2
Volume
Issue:
Vol. 2 (2014): Second AAAI Conference on Human Computation and Crowdsourcing
Track:
Works in Progress
Downloads:
Abstract:
As an alternative to the laborious process of collecting training data from physical robotic platforms for learning robotic grasp quality prediction, we explore the use of surrogate training data from crowd-sourced evaluations of images of robotic grasps. We show that in certain regions of the grasp feature space, grasp predictors trained with this surrogate data were almost as accurate as predictors built using data from physical testing with robots.
DOI:
10.1609/hcomp.v2i1.13193
HCOMP
Vol. 2 (2014): Second AAAI Conference on Human Computation and Crowdsourcing
ISBN 978-1-57735-682-0