EUVIMEDEUVIMED entdecken
Crossref

From Global to Local: Hierarchical Probabilistic Verification for Reachability Learning

Ebonye Smith, Sampada Deglurkar, Jingqi Li, Gechen Qu, Claire J. Tomlin

IEEE Control Systems Letters · 2026 · 10 · 2137-2142

DOI: 10.1109/lcsys.2026.3717040 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Control Systems Letters, 2026. Verfasst von Ebonye Smith und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 29 Literaturangaben. Gefördert von: NSF Safe Learning Enabled Systems, DARPA Assured Autonomy, Assured Neuro-Symbolic Reasoning (ANSR), and Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT) programs, National Aeronautics and Space Administration University Leadership Initiative (NASA ULI) Safe Aviation Autonomy program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hamilton–Jacobi (HJ) reachability provides formal safety guarantees for nonlinear systems. However, it becomes computationally intractable in high-dimensional settings, motivating learning-based approximations that may introduce unsafe errors or overly optimistic safe sets. In this work, we propose a hierarchical probabilistic verification framework for reachability learning that bridges offline global certification and online local refinement. We first construct a coarse, conservative under-approximation of the reach-avoid safe set using scenario optimization, providing an efficient global probabilistic certificate. We then introduce an online local refinement module that is structurally anchored to the global certificate and recovers regions excluded by the global verification. This refinement reduces conservatism while focusing computation on critical regions of the state space. Integrated with a condition-based switching mechanism between a learned reachability policy and a model-based controller, the proposed framework improves success rates in goal-reaching tasks with safety constraints, as demonstrated in drone-racing simulation experiments.

Förderung

  • NSF Safe Learning Enabled Systems
  • DARPA Assured Autonomy, Assured Neuro-Symbolic Reasoning (ANSR), and Transfer from Imprecise and Abstract Models to Autonomous Technologies (TIAMAT) programs
  • National Aeronautics and Space Administration University Leadership Initiative (NASA ULI) Safe Aviation Autonomy program
  • NSF Graduate Research Fellowship Program
  • Oden Institute Fellowship

Zitieren

APA

Smith, E., Deglurkar, S., Li, J., Qu, G., & Tomlin, C. J. (2026). From Global to Local: Hierarchical Probabilistic Verification for Reachability Learning. IEEE Control Systems Letters, 10, 2137-2142. https://doi.org/10.1109/lcsys.2026.3717040

Vancouver

Smith E, Deglurkar S, Li J, Qu G, Tomlin CJ. From Global to Local: Hierarchical Probabilistic Verification for Reachability Learning. IEEE Control Systems Letters. 2026;10:2137-2142. doi:10.1109/lcsys.2026.3717040

BibTeX
@article{Smith2026,
  author = {Smith, Ebonye and Deglurkar, Sampada and Li, Jingqi and Qu, Gechen and Tomlin, Claire J.},
  title = {From Global to Local: Hierarchical Probabilistic Verification for Reachability Learning},
  journal = {IEEE Control Systems Letters},
  year = {2026},
  volume = {10},
  pages = {2137--2142},
  doi = {10.1109/lcsys.2026.3717040}
}
Kostenlos starten →