Article

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

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.

Part of the event: OpenFlyV2 releases paper on onboard vision-language-action model

This page provides a summary and source link only.