A reinforcement learning controller called TD3-HD, combining TD3 with Hindsight Experience Replay and dimension-wise clipping, is claimed to keep a simulated satellite stable when one reaction wheel fails.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Intelligent Control of Spacecraft Reaction Wheel Attitude Using Deep Reinforcement Learning
A reinforcement learning controller called TD3-HD, combining TD3 with Hindsight Experience Replay and dimension-wise clipping, is claimed to keep a simulated satellite stable when one reaction wheel fails.