Learning Symbolic Representations for High-Level Robot Planning

This video describes our research on learning abstract symbolic representations for planning. We show that, given a set of motor skills, a robot can learn an abstract representation - autonomously, and starting with its own sensorimotor space - that provably supports high-level planning.

For more information on this project, please visit:
http://irl.cs.brown.edu/orig_sym.php

For more information about the Intelligent Robot Lab at Brown, see:
http://irl.cs.brown.edu

The journal article is:
G.D. Konidaris, L.P. Kaelbling, and T. Lozano-Perez. "From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning". Journal of Artificial Intelligence Research 61, pages 215-289, January 2018.