SACBFs guarantee continuous-time safety and finite-time reach-and-remain under zero-order-hold control by estimating inter-sample barrier evolution with Taylor upper bounds and adding a relaxed variant for multiple constraints.
A framework for worst- case and stochastic safety verification using barrier certificates,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
CBF-informed rewards for multi-agent RL achieve higher task performance and lower sensitivity to hyperparameters than heuristic baselines in a simulated four-way intersection with connected automated vehicles.
Safe RL by restricting policies to forward-invariant stabilizing actions, demonstrated on quadcopter hover control.
citing papers explorer
-
Sampling-Aware Control Barrier Functions for Safety-Critical and Finite-Time Constrained Control
SACBFs guarantee continuous-time safety and finite-time reach-and-remain under zero-order-hold control by estimating inter-sample barrier evolution with Taylor upper bounds and adding a relaxed variant for multiple constraints.
-
Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehicles
CBF-informed rewards for multi-agent RL achieve higher task performance and lower sensitivity to hyperparameters than heuristic baselines in a simulated four-way intersection with connected automated vehicles.
-
Learning over Forward-Invariant Policy Classes: Reinforcement Learning without Safety Concerns
Safe RL by restricting policies to forward-invariant stabilizing actions, demonstrated on quadcopter hover control.