Article

OpenFlyV2: An 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 authors built a simulation dataset of approximately 70,000 navigation trajectories and 60,000 vision-language instruction-response pairs. On an NVIDIA Jetson Orin NX, the model runs fully onboard and generates action chunks of 12 waypoints each at 10 Hz.

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

This page provides a summary and source link only.