Wayve, a London-based autonomous-driving startup, has developed an AI driving system that learns like humans. The company has pulled in $2.8 billion from investors and strategic partners, including Nvidia, Mercedes-Benz, and Nissan.
How it Works
Wayve’s system uses end-to-end machine learning to navigate roadways, instantly translating sensor-generated data into driving decisions. This approach differs from traditional methods, which rely on software coding and high-definition maps to create preset rules for the car’s response.
Wayve’s CEO, Alex Kendall, believes the company’s system can be licensed to any driverless-car developer, as it is designed to work with a wide array of sensors and AI chips. The company has successfully tested its AI driving system in hundreds of cities worldwide without initial prep work.
Industry Competition
Competition in the autonomous-driving industry is intensifying, with Alphabet’s Waymo expanding its services to offer paid rides to the public in about a dozen cities. Many autonomous-driving developers are now deploying end-to-end learning into their systems.
However, the AI-centric approach raises concerns about the safety and interpretability of the vehicle’s driving decisions. Wayve’s engineers believe their system produces a safety map of unfolding traffic situations and identifies safe paths for the vehicle.
Original reporting: Appleton, WI News Feed (HLL/CB) — read the source article.
