A transformer trained on real table tennis data predicts ball states and is swapped at deployment into simulation-trained policies via SPAD to reduce the sim-to-real gap without retraining.
To- wards human-level learning of complex physical puzzles,
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
-
Bridging the sim2real gap in the table tennis robot with a transformer-based ball states predictor
A transformer trained on real table tennis data predicts ball states and is swapped at deployment into simulation-trained policies via SPAD to reduce the sim-to-real gap without retraining.