asRoBallet achieves the first hardware deployment of an end-to-end RL policy for a humanoid ballbot by training in a high-fidelity simulation that models discrete roller mechanics and multi-channel friction for zero-shot transfer.
Reinforcement Learning for Ballbot Navigation in Uneven Terrain
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
-
asRoBallet: Closing the Sim2Real Gap via Friction-Aware Reinforcement Learning for Underactuated Spherical Dynamics
asRoBallet achieves the first hardware deployment of an end-to-end RL policy for a humanoid ballbot by training in a high-fidelity simulation that models discrete roller mechanics and multi-channel friction for zero-shot transfer.