# OpenFlyV2 releases onboard vision-language-action model for aerial perception and navigation

- Source: HuggingFace Daily Papers
- Published: 2026-10-29T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/bo1h9wem36zqgb0y1uzfkg8sa
- Original: https://huggingface.co/papers/2610.39287

## Summary

OpenFlyV2 is a unified onboard vision-language-action architecture that uses a shared vision-language representation to support semantic understanding, language-grounded perception, spatial reasoning, and continuous flight control within a single model. The model generates action chunks of 12 waypoints each entirely onboard at 10 Hz on an NVIDIA Jetson Orin NX, and transfers zero-shot from simulation to a real quadrotor, achieving a 48% navigation success rate in four real environments without using real aerial training data.