OpenFlyV2: a 1B onboard VLA model for real-time aerial drone navigation
IPEC-COMMUNITY · hf · 2026-10-30
Shanghai AI Lab, with NWPU, Beihang, SJTU, ZJU, USTC and Telecom's TeleAI, released OpenFlyV2 — a unified vision-language-action model for drones. At just 1B parameters, it runs fully onboard resource-constrained hardware, using shared multimodal representations to close the loop between aerial perception, spatial reasoning and waypoint action execution for tasks like "fly to the red clock tower and hover." The paper appeared on arXiv on Oct 29.
More from Embodied
- ETH Zurich and NVIDIA teach a quadruped robot to solve a Rubik's cube with its feet — lukas_m_ziegler · 2026-10-30
- Robots from Asimov and Menlo Research survive brutal hardware testing — alysha_lobo · 2026-10-30
- XPENG's IRON humanoid robot walks off its new production line, 80%+ core processes automated — ingliguori · 2026-10-30
- Lenovo ThinkSmart View boots mainline Linux 7.x, turning the $30 device into a Claude/OpenAI speaker — DavidBennett__ · 2026-10-30
- Amazon's DreamFAR world model nearly doubles π₀ real-world performance for robot training — CyberRobooo · 2026-10-30
- KAIST's L3G-World Generates Infinite Interactive Worlds in Real Time with Latent 3D Gaussian Memory — kaist-ai · 2026-10-30