Rapidly Evolving Soft Robots via Action Inheritance

The automatic design of soft robots characterizes as jointly optimizing structure and control. As reinforcement learning is gradually used to optimize control, the time-consuming controller training makes soft robots design an expensive optimization problem. Although surrogate-assisted evolutionary...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on evolutionary computation 2024-12, Vol.28 (6), p.1674-1688
Hauptverfasser:	Liu, Shulei, Yao, Wen, Wang, Handing, Peng, Wei, Yang, Yang
Format:	Artikel
Sprache:	eng
Schlagworte:	Computational modeling Encoding Error estimation morphological optimization Optimization Robots soft robot design Soft robotics surrogate-assisted evolutionary algorithm (EA) Task analysis Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!