British startup Wave said on Wednesday it would use the supercomputer infrastructure designed for the firm to process huge amounts of data by its investor Microsoft to develop machine learning (ML) -based models for self-driving vehicles.
Wave’s technology relies on machine learning using camera sensors mounted on the outside of the vehicle, where the system learns from traffic patterns and other drivers’ behavior, rather than the conventional method of relying on detailed digital mapping and coding to tell vehicles how to operate. .
“Microsoft is providing supercomputing muscle. What we’re trying to do today is go beyond what is possible for a commercial cloud offering, “Alex Kendall, Wave’s chief executive, told Reuters. Kendall said that Microsoft would be able to process terabytes of data – 1 trillion bytes, or about the equivalent of about an hour of subscriber video – that Wave’s car produces per minute.
This will help startups as it expands its self-driving technology for trials on last-mile delivery vehicles with UK online grocery technology company Ocado and supermarket chain Asda.
Those grocery delivery trials will begin this year with a human safety operator on board. Kendall added, “We see this as a commercial fleet offer. That’s how we think autonomy is coming to market first. ” Earlier this year, Microsoft took part in a বি 200 million Series B funding round for London-based startups.