Learning to Poke by Poking: Experiential Learning of Intuitive Physics
Preprint 2016 en
Authors
PA
Pulkit Agrawal
AN
Ashvin Nair
PA
Pieter Abbeel
Abstract
1 min read
We investigate an experiential learning paradigm for acquiring an internal model of intuitive physics. Our model is evaluated on a real-world robotic manipulation task that requires displacing objects to target locations by poking. The robot gathered over 400 hours of experience by executing more than 100K pokes on different objects. We propose a novel approach based on deep neural networks for modeling the dynamics of robot's interactions directly from images, by jointly estimating forward and inverse models of dynamics. The inverse model objective provides supervision to construct informative visual features, which the forward model can then predict and in turn regularize the feature space for the inverse model. The interplay between these two objectives creates useful, accurate models that can then be used for multi-step decision making. This formulation has the additional benefit that it is possible to learn forward models in an abstract feature space and thus alleviate the need of predicting pixels. Our experiments show that this joint modeling approach outperforms alternative methods.
Mohd Faisal Ibrahim, Aqilah Baseri Huddin, Fazida Hanim Hashim, Mardina Abdullah, Ashrani Aizzuddin Abd. Rahni, Seri Mastura Mustaza, Aini Hussain, Mohd Hairi Mohd Zaman
International Journal of Evaluation and Research in Education (IJERE)
Discussion(0)
No comments yet. Be the first to comment.