Oxbotica is set to use advanced Artificial intelligence (AI) in the metaverse to accelerate the safe and efficient deployment of AV technology, reducing carbon emissions generated by vehicles driving actual miles.
Oxbotica Metadriver is a suite of tools that includes virtual world simulation, automated discovery of challenging scenarios, and real-time data expansion.
Metadriver generates a wide range of scenarios which are used to test and refine AV operations and behaviours without the need for a driver, which accelerates commercial readiness. Metadriver also uses real-world gathered data, to provide digital twin representation.
AI technology has learnt to automatically seek out rare, unusual, and unseen scenarios which allows testing of autonomous systems against “corner cases” and for the systems to handle them. Metadriver offers unseen scenario discovery rates at an average of 1,000 times faster than normal testing methods and up to 35,000 times faster in certain situations.
The unique capabilities of MetaDriver enable targeted and diverse testing, which will give AV operators confidence that their vehicles are equipped and operate safely in their specialised environments.
Founder and CTO of Oxbotica, Paul Newman, has said: “Oxbotica MetaDriver is a suite of tools that offers so much more than straight forward simulation. Using the metaverse in this way provides us and our customers with practically unlimited test challenges, revolutionising how we are accelerating AV commercial deployment to make the Earth move.
“Oxbotica MetaDriver allows us to do the hard miles without the conventional need to physically drive the miles. The autonomous vehicle industry has become over indexed on the number of miles travelled as a synonym for safety, but what we actually care about is coverage of hard cases, not the endless miles endured. Oxbotica MetaDriver addresses this in a new and exciting way.”
Using Metadriver’s data expansion, testing can be done in all conditions whether it be rain, snow, fog and even day and night, eliminating the need to wait for various weather conditions in real-world testing.