Neural-net-controlled drone flies stably in real tests, tolerant of latency
yacineMTB · x · 2026-09-28
yacineMTB shared progress on flying real drones with neural networks: he tested the same networks across every drone, and this flight was stable due to lower latency (less WiFi interference) — the network is tolerant of latency, though real flight latency is near zero. He's soldering and assembling new drone hardware to continue testing.
Related event: Neural Network Flies Real Drone Stably in Low-Latency Conditions(2 posts)→
More from Embodied
- Drone as proof: same infrastructure can do sim2real in the general case — yacineMTB · 2026-09-28
- Yacine demos general sim2real pipeline: policy trained in just two minutes — yacineMTB · 2026-09-28
- Only 7 Years: From Kicked Robot Dogs to a Robotic Leap — alvelda · 2026-09-28
- InternW0-Δ: A World Action Model Trained on 20K+ Hours of Open Robot Data, Fully Open-Sourced — Xingyu Miao · 2026-09-28
- Berkeley's Morphometric Imitation Hits 89.3% Zero-Shot Real-World Success Across 3 Robot Hands — Berkeley · 2026-09-28
- SolidBot moves real steel: post-processed robot programs now heading into TCP and accuracy tests — MatthewChang · 2026-09-28