Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Data is 👑 Our foundation model learns from globally diverse, unlabelled data. Without telling it how to drive or naming different scene elements, our AI learns patterns and behaviours. Our results this week demonstrate how rapidly our AI can learn new behaviours, finding that with hundreds of hours worth...

17,178 görüntüleme • 1 yıl önce •via X (Twitter)

9 Yorum

Alex Kendall profil fotoğrafı
Alex Kendall1 yıl önce

Dive into the data in our blog

The Rundown AI profil fotoğrafı
The Rundown AI2 yıl önce

If you're not learning AI in 2024, you're falling behind. Join 500,000+ readers and learn how to use AI in just 5 minutes a day (for free).

Vekay profil fotoğrafı
Vekay1 yıl önce

1. Rent/Buy a Tesla FSD with v13.2.8 2. Do a side by side comparison of both 3. Livestream both without edits Show but don't tell!!!

Oliver Cameron profil fotoğrafı
Oliver Cameron1 yıl önce

So cool. Has the model learned right on red yet?

Alex Kendall profil fotoğrafı
Alex Kendall1 yıl önce

Yep we started seeing this behavior emerge after 100 hours or so of USA data!

Teemu Määttä profil fotoğrafı
Teemu Määttä1 yıl önce

very cool! about the caveats: when you say safe, how safe is it to drive in US, for example with this 500 hours of additional data?

Prashant Rai profil fotoğrafı
Prashant Rai1 yıl önce

Looks so cool

wotz101 profil fotoğrafı
wotz1011 yıl önce

Hey Alex ask NexusV8 how it would perform as a driver :-)

James95113983 profil fotoğrafı
James951139831 yıl önce

Yes data is king, but this example also confirms what many experts have said, at some point more and more and more data would have diminishing return. How to handle edge cases, march of 9s...when will it be driverless? And at that point, what sensors will be used?

Benzer Videolar

Today we're announcing #GAIA1: a 9B parameter world model, trained on 4,700 hours of driving data, able to simulate complex and diverse driving scenes from video, text and action inputs. This model is 480x larger than the preview we shared earlier this year and the results are incredible. These videos are entirely synthetically generated by Wayve's generative AI, GAIA-1. But there is more here than just generating videos, GAIA is an entire world model. A world model allows us to simulate the future, conditioned on video, text and action inputs, which can be leveraged for making informed decisions when driving. Why is this game-changing for autonomous driving? 1. Safety. One limitation with AI systems like today's Large Language Models is that they are autoregressive, next-word prediction algorithms, but aren't necessarily aware of the implications of their decisions. A world model allows us to give our AI the capability to be aware of its decisions, by simulating the future, which is important for self-driving safety. 2. Synthetic training data. I believe synthetic training data is the future for AI, because it is safer, cheaper, and infinitely scalable. GAIA-1 unlocks unprecedented realism and diversity of synthetic data for self-driving. 3. Long-tail robustness. One of the biggest challenges for self-driving is long-tail robustness: dealing with the enormous magnitude of edge cases we see on the road. An advantage of generative AI is its incredible ability to recombine experiences in new ways. This is exciting for self-driving as it means we can learn from two edge case scenarios, and combine them to become a corner case. For example, we can experience driving in fog, and experience of jay-walking pedestrians, and GAIA can learn from these experiences to understand how to generate a fog+jay walking scenario. Check out many more videos in our blog or further technical details in our paper: Or come chat with our team who are at the International Conference on Computer Vision (#ICCV2023) this week in Paris in Booth 32 Jamie Shotton

Alex Kendall

631,833 görüntüleme • 2 yıl önce