Adaptive dynamic programming and deep reinforcement learning for the control of an unmanned surface vehicle: Experimental results

This paper presents a low-level controller for an unmanned surface vehicle based on adaptive dynamic programming and deep reinforcement learning. This approach uses a single deep neural network capable of self-learning a policy, and driving the surge speed and yaw dynamics of a vessel. A simulation...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Control engineering practice Jg. 111; S. 104807
Hauptverfasser:	Gonzalez-Garcia, Alejandro, Barragan-Alcantar, David, Collado-Gonzalez, Ivana, Garrido, Leonardo
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.06.2021
Schlagworte:	Adaptive dynamic programming Backpropagation through time Deep reinforcement learning Marine robotics Unmanned surface vehicle (USV) Backpropagation through time Deep reinforcement learning Unmanned surface vehicle (USV) Marine robotics Adaptive dynamic programming
ISSN:	0967-0661, 1873-6939
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!