Cognitive Guardrails for Open-World Decision Making in Autonomous Drone Swarms
This work addresses safety and reliability issues for autonomous drone swarms in search-and-rescue missions, representing an incremental improvement by combining existing methods.
The paper tackles the problem of autonomous drone swarms struggling with unfamiliar objects in open-world environments by incorporating large language models for reasoning, but addresses their hallucination risks through cognitive guardrails to ensure safe decision-making, with design, simulation, and real-world integration demonstrated.
Small Uncrewed Aerial Systems (sUAS) are increasingly deployed as autonomous swarms in search-and-rescue and other disaster-response scenarios. In these settings, they use computer vision (CV) to detect objects of interest and autonomously adapt their missions. However, traditional CV systems often struggle to recognize unfamiliar objects in open-world environments or to infer their relevance for mission planning. To address this, we incorporate large language models (LLMs) to reason about detected objects and their implications. While LLMs can offer valuable insights, they are also prone to hallucinations and may produce incorrect, misleading, or unsafe recommendations. To ensure safe and sensible decision-making under uncertainty, high-level decisions must be governed by cognitive guardrails. This article presents the design, simulation, and real-world integration of these guardrails for sUAS swarms in search-and-rescue missions.