Hierarchical approximate optimal interaction control of human-centered modular robot manipulator systems: A Stackelberg differential game-based approach

A Stackelberg game-based approximate optimal interaction control approach is presented for human-centered modular robot manipulator (MRM) systems. Joint torque feedback (JTF) technique is utilized to form the MRM dynamic model. The major objective of optimal control with human–robot collaboration (H...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neurocomputing (Amsterdam) Ročník 585; s. 127573
Hlavní autoři: An, Tianjiao, Zhu, Xinye, Ma, Bing, Jiang, Hucheng, Dong, Bo
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 07.06.2024
Témata:
Adaptive dynamic programming
Human–robot collaboration
Interaction control
Modular robot manipulators
Stackelberg differential game
Interaction control
Adaptive dynamic programming
Modular robot manipulators
Stackelberg differential game
Human–robot collaboration
ISSN:0925-2312
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:A Stackelberg game-based approximate optimal interaction control approach is presented for human-centered modular robot manipulator (MRM) systems. Joint torque feedback (JTF) technique is utilized to form the MRM dynamic model. The major objective of optimal control with human–robot collaboration (HRC) is transformed into approximating Stackelberg equilibrium by adopting Stackelberg game governed between the human and the MRM that are regarded as players with different hierarchical level in interaction process. On the basis of the adaptive dynamic programming (ADP), the approximate optimal interaction control policy with HRC task is developed via critic neural network (NN)-based Stackelberg game manner for addressing Hamilton–Jacobian (HJ) equations. The position tracking error is ultimately uniformly bounded (UUB) according to the Lyapunov theory. Experiment results demonstrate the effectiveness of the proposed method.
ISSN:0925-2312
DOI:10.1016/j.neucom.2024.127573