In a more complex sample would just be like the aerodynamics of the drone what happens when there's a gust of wind and the propeller spinning at a certain rate. In those cases, it's probably often best to have that be an initial guess for a learning based system. And then the more the dynamics are very complicated like pixels to some decision, there's just no possible way to model that parametrically. You just have to, you have to learn it. So I think our journey has been one of just figuring out when to use just like learning end to end.

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