Hierarchical Safe and Robust UAV Path Planning Based on Large Language Models

Summary

This paper proposes an LLM-based hierarchical framework for safe and robust UAV path planning, combining a Prompt–RAG–Validator safety mechanism with a grid cost map and the A* algorithm. The authors test it on multi-constraint tasks, risk-zone planning, incomplete inputs, and prompt injection attacks. On the template-derived benchmark, a deterministic regex/slot parser outperformed the LLM pipeline on safety, with no dangerous outputs, while the LLM pipeline offers more flexibility for diverse phrasing.

Related items

• MediumGitLab patches a max-severity regex flaw alongside five high-severity bugsSimilar attack · CSO Online
• HighCVE-2026-96893: GitLab EE prompt injection into AI agent instructions via conversation contextSimilar attack · NVD/CVE Database
• HighCVE-2026-109331: Network-AI security control bypass in ClaudeHookBridge PreToolUse hookSimilar attack · NVD/CVE Database
• InfoContext Engineering for Application Security | Endor LabsSimilar attack · Endor Labs Blog
• InfoIntroducing AI Coding Agent Governance: Using Hooks to Bring Visibility to the ADLC | Endor LabsSimilar attack · Endor Labs Blog