Conformal recovery-deadline certificates supply distribution-free finite-sample upper bounds on recovery time for adapting controllers in runtime assurance, with proven marginal, weighted, and Mondrian coverage guarantees demonstrated on spacecraft and pendulum testbeds.
Adaptive shielding for safe reinforcement learning under hidden-parameter dynam- ics shifts
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A hybrid spacecraft autonomy architecture combines a grammar-constrained foundation-model commander, rapid motor adaptation controller, and LTL runtime shield, achieving 84% valid actions, 94-98% fault recovery, and 94.5% autonomous operation on a 6-DOF Basilisk testbed.
A latent Q-Barrier shield learns context, dynamics, and cost critic to enforce safety constraints at action level in in-context RL, with a conditional barrier-margin guarantee and benchmark gains.
citing papers explorer
-
Conformal Recovery-Deadline Certificates for Runtime Assurance of Adapting Controllers
Conformal recovery-deadline certificates supply distribution-free finite-sample upper bounds on recovery time for adapting controllers in runtime assurance, with proven marginal, weighted, and Mondrian coverage guarantees demonstrated on spacecraft and pendulum testbeds.
-
Reliability-Asymmetric Spacecraft Autonomy: Co-Designing a Capable Learned GNC Stack with a Verified, Adaptation-Aware Runtime Shield
A hybrid spacecraft autonomy architecture combines a grammar-constrained foundation-model commander, rapid motor adaptation controller, and LTL runtime shield, achieving 84% valid actions, 94-98% fault recovery, and 94.5% autonomous operation on a 6-DOF Basilisk testbed.
-
Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
A latent Q-Barrier shield learns context, dynamics, and cost critic to enforce safety constraints at action level in in-context RL, with a conditional barrier-margin guarantee and benchmark gains.