KIT | KIT-Bibliothek | Impressum | Datenschutz

A Continuous Grasp Representation for the Imitation Learning of Grasps on Humanoid Robots

Do, Martin Minh Thong

Abstract:

Models and methods are presented which enable a humanoid robot to learn reusable, adaptive grasping skills. Mechanisms and principles in human grasp behavior are studied. The findings are used to develop a grasp representation capable of retaining specific motion characteristics and of adapting to different objects and tasks. Based on the representation a framework is proposed which enables the robot to observe human grasping, learn grasp representations, and infer executable grasping actions.


Volltext §
DOI: 10.5445/IR/1000047789
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Hochschulschrift
Publikationsjahr 2014
Sprache Englisch
Identifikator urn:nbn:de:swb:90-477899
KITopen-ID: 1000047789
Verlag Karlsruher Institut für Technologie (KIT)
Art der Arbeit Dissertation
Fakultät Fakultät für Informatik (INFORMATIK)
Institut Institut für Anthropomatik und Robotik (IAR)
Prüfungsdaten 12.06.2014
Referent/Betreuer Dillmann, R.
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page