

The latest version of the dataset can be downloaded from: It has been later extended and used within the European project AMARSi as the benchmark dataset to evaluate the performance of different movement generator algorithms. This dataset was initially used to validate the performance of SEDS in ( Khansari & Billard, TRO 2011).

1-2 Illustration of LASA Handwriting DataSet. In total a library of 30 human handwriting motions were collected, of which 26 each correspond to one single pattern, the remainingįour motions each include more than one pattern (called Multi Models).įig. These demonstrations may intersect each other. Initial positions (but fairly close to each other) and ending to the same final point. For each motion, the user was asked to draw 7 demonstrations of a desired pattern, by starting from different This dataset contains a library of 2D handwriting motions recorded from

Downloads Stable Estimator of Dynamical Systems (SEDS):
