Saved in:
Bibliographic Details
Main Authors: Margapuri, Venkat, Kazanjian, Garik, Kosaraju, Naren
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.20093
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914053948964864
author Margapuri, Venkat
Kazanjian, Garik
Kosaraju, Naren
author_facet Margapuri, Venkat
Kazanjian, Garik
Kosaraju, Naren
contents This study proposes a hybrid safety verification framework for closed-loop multi-agent systems under bounded stochastic disturbances. The proposed approach augments control barrier functions with a novel $ψ$-weighted formulation that encodes directional control alignment between agents into the safety constraints. Deterministic admissibility is combined with empirical validation via Monte Carlo rollouts, and a PAC-style guarantee is derived based on margin-aware safety violations to provide a probabilistic safety certificate. The results from the experiments conducted under different bounded stochastic disturbances validate the feasibility of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid Safety Verification of Multi-Agent Systems using $ψ$-Weighted CBFs and PAC Guarantees
Margapuri, Venkat
Kazanjian, Garik
Kosaraju, Naren
Robotics
This study proposes a hybrid safety verification framework for closed-loop multi-agent systems under bounded stochastic disturbances. The proposed approach augments control barrier functions with a novel $ψ$-weighted formulation that encodes directional control alignment between agents into the safety constraints. Deterministic admissibility is combined with empirical validation via Monte Carlo rollouts, and a PAC-style guarantee is derived based on margin-aware safety violations to provide a probabilistic safety certificate. The results from the experiments conducted under different bounded stochastic disturbances validate the feasibility of the proposed approach.
title Hybrid Safety Verification of Multi-Agent Systems using $ψ$-Weighted CBFs and PAC Guarantees
topic Robotics
url https://arxiv.org/abs/2509.20093