There's a few layers there and we do a reason about a lot of those layers together. At this layer, we do something like 500 iterations per second. And this is thinking about how to balance the rotor aerodynamics with the motion, the orientation of the drone with things like not crashing into obstacles. That's using basically a quadratic approximation of a lot of different objectives in the dynamics of the drone to reason together. But at the end of the day, it's an optimization. It's more of a second order optimization that's being solved.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode