Physical human-robot interaction tasks require robots that can detect and react to external perturba-
tions caused by the human partner. In this contribution, we present a machine learning approach for
detecting, estimating, and compensating for such external perturbations using only input from stan-
dard sensors. This machine learning approach makes use of Dynamic Mode Decomposition (DMD),
a data processing technique developed in the field of fluid dynamics which is applied to robotics for
the first time.