UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios

TL;DR

UAVBench provides a comprehensive, standardized dataset and benchmark for evaluating the reasoning and decision-making capabilities of large language models in autonomous UAV systems, addressing a critical gap in systematic assessment tools.

Contribution

This work introduces UAVBench, a large, validated dataset of UAV flight scenarios and a reasoning-oriented extension, enabling detailed evaluation of LLMs in UAV-specific tasks and ethics-aware decision-making.

Findings

Strong performance in perception and policy reasoning by LLMs

Persistent challenges in ethics-aware decision-making

Resource constraints impact LLM reasoning abilities

Abstract

Autonomous aerial systems increasingly rely on large language models (LLMs) for mission planning, perception, and decision-making, yet the lack of standardized and physically grounded benchmarks limits systematic evaluation of their reasoning capabilities. To address this gap, we introduce UAVBench, an open benchmark dataset comprising 50,000 validated UAV flight scenarios generated through taxonomy-guided LLM prompting and multi-stage safety validation. Each scenario is encoded in a structured JSON schema that includes mission objectives, vehicle configuration, environmental conditions, and quantitative risk labels, providing a unified representation of UAV operations across diverse domains. Building on this foundation, we present UAVBench_MCQ, a reasoning-oriented extension containing 50,000 multiple-choice questions spanning ten cognitive and ethical reasoning styles, ranging from aerodynamics and navigation to multi-agent coordination and integrated reasoning. This framework enables interpretable and machine-checkable assessment of UAV-specific cognition under realistic operational contexts. We evaluate 32 state-of-the-art LLMs, including GPT-5, ChatGPT-4o, Gemini 2.5 Flash, DeepSeek V3, Qwen3 235B, and ERNIE 4.5 300B, and find strong performance in perception and policy reasoning but persistent challenges in ethics-aware and resource-constrained decision-making. UAVBench establishes a reproducible and physically grounded foundation for benchmarking agentic AI in autonomous aerial systems and advancing next-generation UAV reasoning intelligence. To support open science and reproducibility, we release the UAVBench dataset, the UAVBench_MCQ benchmark, evaluation scripts, and all related materials on GitHub at https://github.com/maferrag/UAVBench