The traditional approach used by all of Wayve’s competitors relies on HD-maps, expensive sensor suites and hand-coded rules that tell the car how to drive. Wayve have built a system that learns end-to-end with machine learning. It is the first in the world to drive on urban roads it has never been on before.
Their model learns both lateral and longitudinal control (steering and acceleration) of the vehicle with end-to-end deep learning. Uncertainty is propogated throughout the model, which allows it to learn features from the input data which are most relevant for control, making computation very efficient.
This massively reduces the sensor & compute cost (and power requirements) to less than 10% of traditional approaches.
Assuming other independent observers can confirm these claims, it looks like a UK startup just leap-frogged the entire autonomous car space.