A fully Bayesian Hamiltonian Gaussian Process learns energy-consistent dynamics from input-output data by inferring hidden states and hyperparameters including damping coefficients.
Safelearninginrobotics:Fromlearning-based controltosafereinforcementlearning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Replicates SPARK humanoid safety filters and stress-tests them under crowding, noise, and delays, showing trade-offs in goal tracking versus collision reduction.
citing papers explorer
-
Learning Dynamics from Input-Output Data with Hamiltonian Gaussian Processes
A fully Bayesian Hamiltonian Gaussian Process learns energy-consistent dynamics from input-output data by inferring hidden states and hyperparameters including damping coefficients.
-
Adversarial Stress Testing of SPARK Humanoid Safety Filters
Replicates SPARK humanoid safety filters and stress-tests them under crowding, noise, and delays, showing trade-offs in goal tracking versus collision reduction.