mlsanityData to 14 Oct 2026

Cognition Envelopes for Bounded Decision Making in Autonomous UAS Operations

arXiv 2510.26905 ↗First posted 30 Oct 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 61 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

14 of 61 references.

References · 14

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  2. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 365
  3. 2023AerialVLN: Vision-and-Language Navigation for UAVscited by 121
  4. 2021AI in Finance: Challenges, Techniques and Opportunitiescited by 81
  5. 2023Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agentscited by 69
  6. 2025UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobilitycited by 49
  7. 2021Run Time Assurance for Safety-Critical Systems: An Introduction to Safety Filtering Approaches for Complex Control Systemscited by 27
  8. 2023Reasoning about the Unseen for Efficient Outdoor Object Navigationcited by 13
  9. 2025Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Surveycited by 10
  10. 2025From Prompts to Protection: Large Language Model-Enabled In-Context Learning for Smart Public Safety UAVcited by 10
  11. 2020The Next Generation of Human-Drone Partnerships: Co-Designing an Emergency Response Systemcited by 7
  12. 2025FlySearch: Exploring how vision-language models explorecited by 7
2 more
  1. 2025Coverage Path Planning for Holonomic UAVs via Uniaxial-Feasible, Gap-Severity Guided Decompositioncited by 2
  2. 2025Validating Terrain Models in Digital Twins for Trustworthy sUAS Operationscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Cognitive Guardrails for Open-World Decision Making in Autonomous Drone Swarms
  2. 2025UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios
  3. 2025General-Purpose Aerial Intelligent Agents Empowered by Large Language Models
  4. 2026A Cognitive Architecture for Shared Autonomy in AUV Operations ↗
  5. 2024Probabilistic Mission Design for Neuro-Symbolic Unmanned Aircraft Systems
  6. 2026Reasoning Knowledge-Gap in Drone Planning via LLM-based Active Elicitation
  7. 2025CognitiveDrone: A VLA Model and Evaluation Benchmark for Real-Time Cognitive Task Solving and Reasoning in UAVs
  8. 2026AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents