Bi-level RL decouples center-of-mass planning from thrust control in underactuated blimps, outperforming fixed-CoM and PID controllers in tracking accuracy and sim-to-real transfer on a 27-goal set.
A hierarchical deep reinforcement learning framework with high efficiency and generalization for fast and safe navigation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bi-Level Reinforcement Learning Control for an Underactuated Blimp via Center-of-Mass Reconfiguration
Bi-level RL decouples center-of-mass planning from thrust control in underactuated blimps, outperforming fixed-CoM and PID controllers in tracking accuracy and sim-to-real transfer on a 27-goal set.