Dynamic soaring emerges from local state-feedback control learned by reinforcement learning, enabling robust omnidirectional navigation in shear flows without cycle-level planning.
Efficient collective swimming by harnessing vortices through deep reinforcement learning.Proceedings of the National Academy of Sciences, 115(23):5849–5854, 2018
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning step-level dynamic soaring in shear flow
Dynamic soaring emerges from local state-feedback control learned by reinforcement learning, enabling robust omnidirectional navigation in shear flows without cycle-level planning.