body { -ms-overflow-style: scrollbar; overflow-y: scroll; overscroll-behavior-y: none; } .errorContainer { background-color: #FFF; color: #0F1419; max-width: 600px; margin: 0 auto; padding: 10%; font-family: Helvetica, sans-serif; font-size: 16px; } .errorButton { margin: 3em 0; } .errorButton a { background: #1DA1F2; border-radius: 2.5em; color: white; padding: 1em 2em; text-decoration: none; } .errorButton a:hover, .errorButton a:focus { background: rgb(26, 145, 218); } .errorFooter { color: #657786; font-size: 80%; line-height: 1.5; padding: 1em 0; } .errorFooter a, .errorFooter a:visited { color: #657786; text-decoration: none; padding-right: 1em; } .errorFooter a:hover, .errorFooter a:active { text-decoration: underline; } #placeholder, #react-root { display: none !important; } body { background-color: #FFF !important; }

JavaScript is not available.

We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using twitter.com. You can see a list of supported browsers in our Help Center.

Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2023 Twitter, Inc.

Conversation

To scale self-driving technology, we believe you need an adaptable driving intelligence that can be applied to different vehicles and drive in new cities.

Embedded video

GIF

1

4

11

Last year during our multi-city test we took a model that we had trained in London to 5 UK cities it had not seen before. In each city, we saw the model’s performance generalised. wayve.ai/blog/unlocking

Embedded video

0:03

56 views

1

2

Our next breakthrough shows that we can power both a passenger car and a light-commercial van using the same AI system. That’s the same model, driving on the same route, but on two different vehicles without any interconnected communications.

Autonomous Van Runs

No two driving scenarios are ever the same. That's why it's important that our autonomous vehicle system is able to adapt to new situations it encounters on ...

1

1

From this testing we drew 3 conclusions: 1) We could train a driving model capable of generalising between vehicle platforms. 2) We did so with a comparably small dataset from the new van, confirming that we were able to leverage the wider data corpus for generalisation.

1

2

3) We observed an uplift in performance on both vehicles by using a combination of car and van data to train the model. This joint data corpus outperformed a single vehicle data corpus on our sim evaluation benchmarks.

1

2

We attribute the performance uplift to the greater diversity of driving states observed in a joint data corpus compared to a single vehicle data corpus.

Generalising from cars to vans

The same AI system is autonomously driving 2 different vehicles, a car and a van, at the same time. The AV technology between the two vehicles is not interco...

8:31 AM · Sep 27, 2022

Replying to

Achieving the generalisation milestones of multi-city and multi-vehicle is an industry-first and key to unlocking this technology at a global scale.

Wayve Presents: The Industry's First Generalisable AI Driver

The inside story of the Wayve team who created the first AI Driver that can generalise to different cities and vehicle types, a grand challenge of self-drivi...

5