Learning inverse kinematics with structured prediction

Learning inverse kinematics of robots with redundant degrees of freedom (DoF) is a difficult problem in robot learning. The difficulty lies in the non-uniqueness of the inverse kinematics function. Existing methods tackle non-uniqueness by segmenting the configuration space and building a global sol...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Bocsi, Botond, Nguyen-Tuong, Duy, Csato, Lehel, Scholkopf, Bernhard, Peters, Jan
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Joints Kernel Kinematics Mathematical model Prediction algorithms Robots Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!