British startup Wayve has created a machine learning model that drives two different types of vehicles: a car and a delivery van. Writes about it Technology Review.
According to the company, both types of vehicles are equipped with the same set of six cameras. However, due to the structural features of the van body, the sensors were placed higher and at different angles than the sedan.
As a result, the input to the model differs between vehicles. However, AI has learned to control them from any viewing angle, the company said. The algorithm has also adapted to the larger size and weight of the van.
Wayve used reinforcement learning and thousands of hours of riding data to train the model. Engineers ran a driving simulation that learned how to drive a van in just 80 hours.
According to the developers, the model adapted to new cars faster than expected at the design stage.
The engineers then tested the algorithm on the streets of London. According to Wayve safety operator Naomi Standard, the van handled the city’s narrow streets well and successfully navigated various obstacles.
The developers claim that this is the first time that the same AI driver has learned to drive different types of cars. In their opinion, this will help the system scale faster and be implemented in various cities without significant modifications.
“It’s like when you go to a new place and rent a car, you can still drive,” Wayve’s vice president of technology, Jeff Hawke, said in a statement.
In the future, the company plans to be the first in the market to deploy computer vision-based self-driving cars in 100 cities.
Recall that in September, Cruise began delivering orders from Walmart supermarkets using unmanned vehicles.
In August, Waymo launched a robot taxi without a security driver behind the wheel in downtown Phoenix.
Subscribe to Cryplogger news in Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER
British startup Wayve has created a machine learning model that drives two different types of vehicles: a car and a delivery van. Writes about it Technology Review.
According to the company, both types of vehicles are equipped with the same set of six cameras. However, due to the structural features of the van body, the sensors were placed higher and at different angles than the sedan.
As a result, the input to the model differs between vehicles. However, AI has learned to control them from any viewing angle, the company said. The algorithm has also adapted to the larger size and weight of the van.
Wayve used reinforcement learning and thousands of hours of riding data to train the model. Engineers ran a driving simulation that learned how to drive a van in just 80 hours.
According to the developers, the model adapted to new cars faster than expected at the design stage.
The engineers then tested the algorithm on the streets of London. According to Wayve safety operator Naomi Standard, the van handled the city’s narrow streets well and successfully navigated various obstacles.
The developers claim that this is the first time that the same AI driver has learned to drive different types of cars. In their opinion, this will help the system scale faster and be implemented in various cities without significant modifications.
“It’s like when you go to a new place and rent a car, you can still drive,” Wayve’s vice president of technology, Jeff Hawke, said in a statement.
In the future, the company plans to be the first in the market to deploy computer vision-based self-driving cars in 100 cities.
Recall that in September, Cruise began delivering orders from Walmart supermarkets using unmanned vehicles.
In August, Waymo launched a robot taxi without a security driver behind the wheel in downtown Phoenix.
Subscribe to Cryplogger news in Telegram: Cryplogger AI – all the news from the world of AI!
Found a mistake in the text? Select it and press CTRL+ENTER