Hacker News Reader

Comment by xedeon | Hacker News Reader

You completely just glossed over how Sebastian Thrun has changed his mind about Lidar and went straight to disparaging Scoble.

A valid argument on why you think Thrun is wrong would have served stance point better.

View on HN

I respect Thrun. He's a brilliant researcher and a very smart man. I've read his "Probabilistic robotics" book. I can also tell you right now that he's _wrong_. There will not be purely optical FSD on non-modified city roads shared with humans in the foreseeable future. Highways? Maybe. But not city roads. The problem is exponentially more complex there. It is even more so on top of that if you have to _estimate_ rather than _measure_ distances to things. It is true that the LIDAR does not simplify it all that much, but LIDAR at least gives you a fairly good idea of where all the obstacles are so you could avoid them. That's what it's for. Cameras fed into neural nets have to _guess_ based on appearance of things and stereoscopy. They are also subject to all the other limitations of optical sensors: rain, snow, fog, dirt on the camera (anyone who has a Tesla knows the cameras get dirt on them pretty easily), and just plain not recognizing an obstacle if it's positioned in a way that the neural network just happened to not generalize for.

We (humans) can only do this purely optically because we have general intelligence and extensive knowledge about the world. The FSD computer in your Tesla does not.

BTW, can you give a quick summary on sensors for autonomous ships?

Do they use lidar/radar/magnetic sensors ?!

Naively, i assume waves/spray is a one-time technical hurdle, but after this it is much easier to get autonomous ships?

Just FYI, many other high-level experts on this space like Anthony Levandowski who actually worked with Sebastian Thrun after meeting him at the 2005 DARPA Grand Challenge. Said the same thing.

There's a reason why I asked if you could share your work. Because those two individuals are clearly at the top of their field. If your thesis is correct, then it's easily worth 100+M if not 1B+ USD in value.

It's easy to be hyper critical, compared to actually being in the trenches trying to solve these hard problems.

https://www.youtube.com/watch?v=fNgEG5rCav4&t=110

Reply on news.ycombinator.com