DFKI-LT - Long Short-Term Memory for Affordances Learning

Sergio Roa, Geert-Jan Kruijff
Long Short-Term Memory for Affordances Learning
in: Lola Caņamero, Pierre-Yves Oudeyer, Christian Balkenius (eds.):
2 Proceedings of the 9th International Conference on Epigenetic Robotics,
Lund University Cognitive Studies number 146, Pages 235-236, Venice, Italy, o.A., 11/2009

 
This paper addresses the problem of sensorimotor learning from the perspective of affordances learning of simple objects. We are developing a scenario where a robotic arm interacts with a polyflap, a simple 3-dimensional geometrical object. We perform experiments with a simulated arm using a physics simulator, but we plan to use also a real arm. The robot interacts with the object by pushing it in different ways. We use Recurrent Neural Networks to predict the arm and object poses during this interaction, given a discrete set of random actions that the robot can produce.
 
Files: BibTeX, RoaKruijffEPIROB09.pdf