AutoIncSFA and vision-based developmental learning for humanoid robots

Varun Raj Kompella, Leo Pape, Jonathan Masci, Mikhail Frank, Jurgen Schmidhuber
2011 2011 11th IEEE-RAS International Conference on Humanoid Robots  
Humanoids have to deal with novel, unsupervised high-dimensional visual input streams. Our new method Au-toIncSFA learns to compactly represent such complex sensory input sequences by very few meaningful features corresponding to high-level spatio-temporal abstractions, such as: a person is approaching me, or: an object was toppled. We explain the advantages of AutoIncSFA over previous related methods, and show that the compact codes greatly facilitate the task of a reinforcement learner
more » ... the humanoid to actively explore its world like a playing baby, maximizing intrinsic curiosity reward signals for reaching states corresponding to previously unpredicted AutoIncSFA features.
doi:10.1109/humanoids.2011.6100865 dblp:conf/humanoids/KompellaPMFS11 fatcat:5l4v6qoc6rbojgooxn7bikagua