TY - GEN
T1 - Transfer entropy for feature extraction in physical human-robot interaction
T2 - 2014 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
AU - Berger, Erik
AU - Müller, David
AU - Vogt, David
AU - Jung, Bernhard
AU - Ben Amor, Heni
PY - 2015/2/12
Y1 - 2015/2/12
N2 - In physical human-robot interaction, robot behavior must be adjusted to forces applied by the human interaction partner. For measuring such forces, special-purpose sensors may be used, e.g. force-torque sensors, that are however often heavy, expensive and prone to noise. In contrast, we propose a machine learning approach for measuring external perturbations of robot behavior that uses commonly available, low-cost sensors only. During the training phase, behavior-specific statistical models of sensor measurements, so-called perturbation filters, are constructed using Principal Component Analysis, Transfer Entropy and Dynamic Mode Decomposition. During behavior execution, perturbation filters compare measured and predicted sensor values for estimating the amount and direction of forces applied by the human interaction partner. Such perturbation filters can therefore be regarded as virtual force sensors that produce continuous estimates of external forces.
AB - In physical human-robot interaction, robot behavior must be adjusted to forces applied by the human interaction partner. For measuring such forces, special-purpose sensors may be used, e.g. force-torque sensors, that are however often heavy, expensive and prone to noise. In contrast, we propose a machine learning approach for measuring external perturbations of robot behavior that uses commonly available, low-cost sensors only. During the training phase, behavior-specific statistical models of sensor measurements, so-called perturbation filters, are constructed using Principal Component Analysis, Transfer Entropy and Dynamic Mode Decomposition. During behavior execution, perturbation filters compare measured and predicted sensor values for estimating the amount and direction of forces applied by the human interaction partner. Such perturbation filters can therefore be regarded as virtual force sensors that produce continuous estimates of external forces.
UR - http://www.scopus.com/inward/record.url?scp=84945190350&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84945190350&partnerID=8YFLogxK
U2 - 10.1109/HUMANOIDS.2014.7041459
DO - 10.1109/HUMANOIDS.2014.7041459
M3 - Conference contribution
AN - SCOPUS:84945190350
T3 - IEEE-RAS International Conference on Humanoid Robots
SP - 829
EP - 834
BT - 2014 IEEE-RAS International Conference on Humanoid Robots, Humanoids 2014
PB - IEEE Computer Society
Y2 - 18 November 2014 through 20 November 2014
ER -