Oxbotica steps into the metaverse

Use of AI can accelerate development of AVs by giving them unlimited test scenarios
Detection, Monitoring & Machine Vision / June 23, 2022
By Adam Hill
Artificial intelligence autonomous vehicles virtual reality metaverse (image courtesy: Oxbotica)
AI learns to automatically seek out rare, unusual, and unseen scenarios (image courtesy: Oxbotica)

Oxbotica says it is using advanced Artificial Intelligence (AI) in the metaverse to accelerate deployment of autonomous vehicle (AV) technology.

AV scenario testing is a crucial part of development without actually driving on real roads, and recent research suggests that AVs will learn quicker if they are exposed to 'one-in-a-million' collision scenarios.

Oxbotica's MetaDriver includes virtual world simulation, automated discovery of challenging scenarios, and real-time data expansion to test AV actions and behaviour in any weather or road conditions.
"The AIs have learnt to automatically seek out rare, unusual, and unseen scenarios, known as 'edge cases', which allows both the testing of autonomy systems against 'corner cases' and for the systems to learn to handle them," the company says in a statement.

MetaDriver "offers edge-case discovery rates at an average of 1,000 times faster than traditional testing methods, and up to 35,000 times faster in some situations", it adds.

“Using the metaverse in this way provides us and our customers with practically unlimited test challenges, revolutionising how we are accelerating AV commercial deployment," says Paul Newman, founder and CTO at Oxbotica.

For more information on companies in this article