A Gaussian Process model learns impact-state-dependent bounce parameters for an impulse contact model across 10 diverse racket rubbers, reducing velocity and spin prediction errors versus constant baselines and supporting online adaptation.
Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ICODE-MPPI uses Input Concomitant Neural ODEs to learn residual dynamics and reduce vehicle cross-tracking error by up to 69% under disturbances compared with standard MPPI.
citing papers explorer
-
Learning Racket-Ball Bounce Dynamics Across Diverse Rubbers for Robotic Table Tennis
A Gaussian Process model learns impact-state-dependent bounce parameters for an impulse contact model across 10 diverse racket rubbers, reducing velocity and spin prediction errors versus constant baselines and supporting online adaptation.
-
Robust Path Tracking for Vehicles via Continuous-Time Residual Learning: An ICODE-MPPI Approach
ICODE-MPPI uses Input Concomitant Neural ODEs to learn residual dynamics and reduce vehicle cross-tracking error by up to 69% under disturbances compared with standard MPPI.