SHIELD learns a generative model of a humanoid's tracking error and uses a stochastic control barrier function to filter reference commands, giving runtime obstacle avoidance with probabilistic safety bounds in hardware.
Learning agile and dynamic motor skills for legged robots,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics
SHIELD learns a generative model of a humanoid's tracking error and uses a stochastic control barrier function to filter reference commands, giving runtime obstacle avoidance with probabilistic safety bounds in hardware.