PL-CBF evaluates a library of fallback policies through parallel finite-horizon rollouts and selects the least invasive safe mode via quadratic programming to certify finite-horizon safety at runtime.
Neural Network Model Predictive Motion Control Applied to Automated Driving With Un- known Friction,
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
-
Policy Library CBF: Finite-Horizon Safety at Runtime via Parallel Rollouts
PL-CBF evaluates a library of fallback policies through parallel finite-horizon rollouts and selects the least invasive safe mode via quadratic programming to certify finite-horizon safety at runtime.