A gain-regularized, parameter-conditioned RNN balances a low-cost 110:1 gearbox robot with matching simulated and real settling times, while naive domain randomization oscillates.
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
-
Quantifying and Visualizing Sim-to-Real Gaps: Physics-Guided Regularization for Reproducibility
A gain-regularized, parameter-conditioned RNN balances a low-cost 110:1 gearbox robot with matching simulated and real settling times, while naive domain randomization oscillates.