State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification of Autonomous Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Waite, Thomas, Geng, Yuang, Turnquist, Trevor, Ruchkin, Ivan, Ivanov, Radoslav
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915292302540800
author Waite, Thomas
Geng, Yuang
Turnquist, Trevor
Ruchkin, Ivan
Ivanov, Radoslav
author_facet Waite, Thomas
Geng, Yuang
Turnquist, Trevor
Ruchkin, Ivan
Ivanov, Radoslav
contents It remains a challenge to provide safety guarantees for autonomous systems with neural perception and control. A typical approach obtains symbolic bounds on perception error (e.g., using conformal prediction) and performs verification under these bounds. However, these bounds can lead to drastic conservatism in the resulting end-to-end safety guarantee. This paper proposes an approach to synthesize symbolic perception error bounds that serve as an optimal interface between perception performance and control verification. The key idea is to consider our error bounds to be heteroskedastic with respect to the system's state -- not time like in previous approaches. These bounds can be obtained with two gradient-free optimization algorithms. We demonstrate that our bounds lead to tighter safety guarantees than the state-of-the-art in a case study on a mountain car.
format Preprint
id arxiv_https___arxiv_org_abs_2502_21308
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification of Autonomous Systems
Waite, Thomas
Geng, Yuang
Turnquist, Trevor
Ruchkin, Ivan
Ivanov, Radoslav
Systems and Control
It remains a challenge to provide safety guarantees for autonomous systems with neural perception and control. A typical approach obtains symbolic bounds on perception error (e.g., using conformal prediction) and performs verification under these bounds. However, these bounds can lead to drastic conservatism in the resulting end-to-end safety guarantee. This paper proposes an approach to synthesize symbolic perception error bounds that serve as an optimal interface between perception performance and control verification. The key idea is to consider our error bounds to be heteroskedastic with respect to the system's state -- not time like in previous approaches. These bounds can be obtained with two gradient-free optimization algorithms. We demonstrate that our bounds lead to tighter safety guarantees than the state-of-the-art in a case study on a mountain car.
title State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification of Autonomous Systems
topic Systems and Control
url https://arxiv.org/abs/2502.21308