How can a robot learn motor representations and use them to build basic affordant reaching and manipulation skills?

In MACSi, we will address the edification of motor skills and generic learned affordances with a complex humanoid robot interacting with objects. This will entail the adaptation and extension of existing model learning and robot control techniques to a challenging context where, rather than a single goal, there is a gradually increasing repertoire of goals whose extension is driven by the learned representations themselves.

Challenge leader : ISIR-UPMC-Paris 6 (Paris). ISIR hosts the iCub humanoid robot on which the achievements will be evaluated.