UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios
This provides a reproducible foundation for benchmarking agentic AI in autonomous aerial systems, addressing a gap for researchers and developers in UAV and AI fields, though it is incremental as it builds on existing LLM and UAV technologies.
The authors tackled the lack of standardized benchmarks for evaluating LLM-based reasoning in autonomous UAV systems by introducing UAVBench, an open dataset of 50,000 validated flight scenarios and 50,000 multiple-choice questions, and found that state-of-the-art LLMs perform well in perception and policy reasoning but struggle with ethics-aware and resource-constrained decision-making.
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