For years, open source has made it easy to build a drone that flies. Projects like Betaflight and INAV matured the basics with stable flight, clean firmware, and reliable control loops. But building a drone that thinks? That has largely remained locked behind corporate walls. Autonomous navigation, perception, real-time decision making, all wrapped in proprietary…
October marked a turning point for Swarm (Subnet 124), Bittensor’s first robotics subnet. In just a few weeks, the team refined their model evaluation system, expanded testing environments. They also took their first real step into the physical world with a successful autonomous drone flight. Smarter Maps, Smarter Models Training AI to navigate the real…
We read Swarm’s Substack article on how their subnet plans to generate revenue — and a few things really stood out. First, their subnet isn’t just running drone simulations for fun. It’s been a live testing ground for developing autonomous models capable of piloting a real quadrotor drone — equipped with LiDAR and precise sensors….
Originally published on Swarm Substack — subscribe for full updates and insights. Swarm (Subnet 124) is a perpetual, on-chain tournament for drone autonomy. If you already speak Bittensor, think of Swarm as a specialized marketplace where validators continuously mint reproducible flight challenges and miners submit pre-trained policies (frozen autopilots) that are scored headlessly and paid according to performance. If you don’t speak Bittensor is…
Swarm, Subnet 124 on Bittensor, is a decentralized AI network on Bittensor that focuses on building an open-source autopilot system for drones. It is a competitive marketplace where different contributors create and test flight plans in simulated environments, aiming to guide drones safely and efficiently to their destinations. The best plans—those that avoid crashes, use…
