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.
Conversation
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
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.
Replying to
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
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.
1
5
Achieving the generalisation milestones of multi-city and multi-vehicle is an industry-first and key to unlocking this technology at a global scale.
5