Saved in:
Bibliographic Details
Main Authors: Granadeno, Pedro Antonio Alarcon, Russell, Arturo Miguel Bernal, Nelson, Sofia, Hernandez, Demetrius, Petterson, Maureen, Murphy, Michael, Scheirer, Walter J., Cleland-Huang, Jane
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.26905
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910040766545920
author Granadeno, Pedro Antonio Alarcon
Russell, Arturo Miguel Bernal
Nelson, Sofia
Hernandez, Demetrius
Petterson, Maureen
Murphy, Michael
Scheirer, Walter J.
Cleland-Huang, Jane
author_facet Granadeno, Pedro Antonio Alarcon
Russell, Arturo Miguel Bernal
Nelson, Sofia
Hernandez, Demetrius
Petterson, Maureen
Murphy, Michael
Scheirer, Walter J.
Cleland-Huang, Jane
contents Cyber-physical systems increasingly rely on foundational models, such as Large Language Models (LLMs) and Vision-Language Models (VLMs) to increase autonomy through enhanced perception, inference, and planning. However, these models also introduce new types of errors, such as hallucinations, over-generalizations, and context misalignments, resulting in incorrect and flawed decisions. To address this, we introduce the concept of Cognition Envelopes, designed to establish reasoning boundaries that constrain AI-generated decisions while complementing the use of meta-cognition and traditional safety envelopes. As with safety envelopes, Cognition Envelopes require practical guidelines and systematic processes for their definition, validation, and assurance. In this paper we describe an LLM/VLM-supported pipeline for dynamic clue analysis within the domain of small autonomous Uncrewed Aerial Systems deployed on Search and Rescue (SAR) missions, and a Cognition Envelope based on probabilistic reasoning and resource analysis. We evaluate the approach through assessing decisions made by our Clue Analysis Pipeline in a series of SAR missions. Finally, we identify key software engineering challenges for systematically designing, implementing, and validating Cognition Envelopes for AI-supported decisions in cyber-physical systems.
format Preprint
id arxiv_https___arxiv_org_abs_2510_26905
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cognition Envelopes for Bounded Decision Making in Autonomous UAS Operations
Granadeno, Pedro Antonio Alarcon
Russell, Arturo Miguel Bernal
Nelson, Sofia
Hernandez, Demetrius
Petterson, Maureen
Murphy, Michael
Scheirer, Walter J.
Cleland-Huang, Jane
Artificial Intelligence
Cyber-physical systems increasingly rely on foundational models, such as Large Language Models (LLMs) and Vision-Language Models (VLMs) to increase autonomy through enhanced perception, inference, and planning. However, these models also introduce new types of errors, such as hallucinations, over-generalizations, and context misalignments, resulting in incorrect and flawed decisions. To address this, we introduce the concept of Cognition Envelopes, designed to establish reasoning boundaries that constrain AI-generated decisions while complementing the use of meta-cognition and traditional safety envelopes. As with safety envelopes, Cognition Envelopes require practical guidelines and systematic processes for their definition, validation, and assurance. In this paper we describe an LLM/VLM-supported pipeline for dynamic clue analysis within the domain of small autonomous Uncrewed Aerial Systems deployed on Search and Rescue (SAR) missions, and a Cognition Envelope based on probabilistic reasoning and resource analysis. We evaluate the approach through assessing decisions made by our Clue Analysis Pipeline in a series of SAR missions. Finally, we identify key software engineering challenges for systematically designing, implementing, and validating Cognition Envelopes for AI-supported decisions in cyber-physical systems.
title Cognition Envelopes for Bounded Decision Making in Autonomous UAS Operations
topic Artificial Intelligence
url https://arxiv.org/abs/2510.26905