UAV-CodeAgents combines multi-agent ReAct reasoning with a fine-tuned vision-language model for pixel-level grounding to generate UAV missions from satellite imagery and text prompts.
Aerial vision-and-dialog navigation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
UAV-CodeAgents: Scalable UAV Mission Planning via Multi-Agent ReAct and Vision-Language Reasoning
UAV-CodeAgents combines multi-agent ReAct reasoning with a fine-tuned vision-language model for pixel-level grounding to generate UAV missions from satellite imagery and text prompts.