Human Push-Recovery: Strategy Selection Based on Push Intensity Estimation

Konferenz: ISR 2016 - 47st International Symposium on Robotics
21.06.2016 - 22.06.2016 in München, Germany

Tagungsband: ISR 2016

Seiten: 8Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Kaul, Lukas; Asfour, Tamim (Institute for Anthropomatics and Robotics, High Performance Humanoid Technologies Lab (H2T) at the Karlsruhe, Institute for Technology, Adenauerring 2, 76131 Karlsruhe, Germany)

We present methods for extracting a fast indicator for push-recovery strategy selection from the data of an inertial measurement unit mounted on a human or humanoid torso. The methods serve the purposes of detecting the beginning, the direction and intensity of the push as well as predicting the feasible recovery strategy. We test our methods on a dataset of 78 push-recovery trials collected with a human subject and show the relation between push intensity and recovery strategy.