Multi-criteria benchmarking of movement generating dynamical systems for learning-from-demonstrations

TitleMulti-criteria benchmarking of movement generating dynamical systems for learning-from-demonstrations
Publication TypeMiscellaneous
Year of Publication2014
AuthorsLemme A, Meirovitch Y, Khansari-Zadeh SMohammad, Flash T, Billard A, Steil JJ
Abstract

This MATLAB benchmark framework was developed to compare different methods for generating goal directed trajectories and extract their specificities, strengths and weaknesses. It allows each user to configure different perturbations which can occur during a movement execution and prepare their models for the given task before a baseline parameter set is used to create comparable results. For more information, please refer to the entry in CITEC's Cognitive Interaction Toolkit Catalogue (CITK): http://toolkit.cit-ec.uni-bielefeld.de/datasets/amarsi-benchmark-framework Software updates und support: https://opensource.cit-ec.de/projects/amarsi

DOI10.4119/unibi/2678439