Title :
Explauto: an open-source Python library to study autonomous exploration in developmental robotics
Author :
Moulin-Frier, Clement ; Rouanet, Pierre ; Oudeyer, Pierre-Yves
Author_Institution :
Flowers Team, Inria/ENSTA-Paristech, Bordeaux, France
Abstract :
The Explauto library provides a common platform to the Developmental Robotics community allowing the integration and comparison of various exploration strategies driving various sensorimotor learning algorithms in various simulated or robotics systems. Many other exploration strategies could be easily integrated into the library, as for example Direction Sampling [7], compression progress [4], empowerment [8] and thus be compared in a proper way on various sensorimotor systems and using various sensorimotor internal models.
Keywords :
application program interfaces; control engineering computing; robots; Explauto library; compression progress strategy; developmental robotics; direction sampling strategy; empowerment strategy; open-source Python library; robot exploration strategy; sensorimotor internal models; sensorimotor learning algorithms; Computational modeling; Computer architecture; Libraries; Open source software; Predictive models; Robot sensing systems;
Conference_Titel :
Development and Learning and Epigenetic Robotics (ICDL-Epirob), 2014 Joint IEEE International Conferences on
Conference_Location :
Genoa
DOI :
10.1109/DEVLRN.2014.6982976
