KIT | KIT-Bibliothek | Impressum | Datenschutz

End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control

Reuss, Moritz; Duijkeren, Niels van; Krug, Robert; Becker, Philipp 1; Shaj, Vaisakh; Neumann, Gerhard 1
1 Institut für Anthropomatik und Robotik (IAR), Karlsruher Institut für Technologie (KIT)

Abstract:

It is well-known that inverse dynamics models can improve tracking performance in robot control. These models need to precisely capture the robot dynamics, which consist of well-understood components, e.g., rigid body dynamics, and effects that remain challenging to capture, e.g., stick-slip friction and mechanical flexibilities. Such effects exhibit hysteresis and partial observability, rendering them, particularly challenging to model. Hence, hybrid models, which combine a physical prior with data-driven approaches are especially well-suited in this setting. We present a novel hybrid model formulation that enables us to identify fully physically consistent inertial parameters of a rigid body dynamics model which is paired with a recurrent neural network architecture, allowing us to capture unmodeled partially observable effects using the network memory. We compare our approach against state-of-the-art inverse dynamics models on a 7 degree of freedom manipulator. Using data sets obtained through an optimal experiment design approach, we study the accuracy of offline torque prediction and generalization capabilities of joint learning methods. ... mehr


Preprint §
DOI: 10.5445/IR/1000147885
Veröffentlicht am 24.06.2022
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2022
Sprache Englisch
Identifikator KITopen-ID: 1000147885
Erschienen in Robotics: Science and Systems XVIII. Ed.: K. Hauser
Veranstaltung 18th Robotics: Science and Systems (2022), New York City, NY, USA, 27.06.2022 – 01.07.2022
Schlagwörter robotics, model learning, impedance control, dynamics
Nachgewiesen in arXiv
Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page