Efficient collective swimming by harnessing vortices through deep reinforcement learning

Fish in schooling formations navigate complex flow fields replete with mechanical energy in the vortex wakes of their companions. Their schooling behavior has been associated with evolutionary advantages including energy savings, yet the underlying physical mechanisms remain unknown. We show that fi...

Celý popis

Podrobná bibliografie

Vydáno v:	Proceedings of the National Academy of Sciences - PNAS Ročník 115; číslo 23; s. 5849
Hlavní autoři:	Verma, Siddhartha, Novati, Guido, Koumoutsakos, Petros
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States 05.06.2018
Témata:	Animals Behavior, Animal - physiology Biomechanical Phenomena Computer Simulation Fishes - physiology Learning - physiology Models, Biological Reinforcement, Psychology Spatial Navigation - physiology Swimming - physiology energy harvesting deep reinforcement learning autonomous navigation recurrent neural networks fish schooling
ISSN:	1091-6490, 1091-6490
On-line přístup:	Zjistit podrobnosti o přístupu
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!