Cognition Envelopes for Bounded AI Reasoning in Autonomous UAS Operations
This addresses safety and reliability issues for autonomous unmanned aerial systems, but appears incremental as it builds on existing safety envelope concepts.
The paper tackles the problem of errors like hallucinations and context misalignments in foundational models used for autonomous UAS operations by introducing Cognition Envelopes to constrain AI reasoning, aiming to improve decision-making without specifying concrete numerical results.
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, overgeneralizations, 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.