Authors:
Vittorio Lippi
and
Raphael Deimel
Affiliation:
Technische Universität Berlin, Fachgebiet Regelungssysteme, Sekretariat EN11, Einsteinufer 17, 10587 Berlin and Germany
Keyword(s):
ProMP, Human Movement, Prediction, Recognition, Time Warping, Phase.
Related
Ontology
Subjects/Areas/Topics:
Human-Machine Interfaces
;
Informatics in Control, Automation and Robotics
;
Modeling, Analysis and Control of Hybrid Dynamical Systems
;
Modeling, Simulation and Architectures
;
Robot Design, Development and Control
;
Robotics and Automation
;
Signal Processing, Sensors, Systems Modeling and Control
;
System Modeling
Abstract:
Probabilistic Movement Primitives (ProMPs) are a widely used representation of movements for human-robot interaction. They also facilitate the factorization of temporal and spatial structure of movements. In this work we investigate a method to temporally align observations so that when learning ProMPs, information in the spatial structure of the observed motion is maximized while maintaining a smooth phase velocity. We apply the method on recordings of hand trajectories in a two-dimensional reaching task. A system for simultaneous recognition of movement and phase is proposed and performance of movement recognition and movement reproduction is discussed.