The largest search engine in Russia, Yandex, revealed a prototype of an autonomous taxi cab in a video yesterday.
The video shows Yandex.Taxi — which will work with on-demand ride services — weaving around obstacles and errant pedestrians as well as avoiding a truck collision. The vehicle is developed in-house using navigation, geolocation, computer vision, and machine learning based on other Yandex products including Yandex.Navigator and Yandex.Maps, said Vladimir Isaev, Yandex.Taxi head of public relations, in a published report.
Notably, Yandex.Taxi uses a Nvidia GTX GPU within the vehicle, as well as a Velodyne lidar unit. The Moscow-based company is using proprietary “custom-built” hardware, in addition to mass market components, but is in talks with partners to create “fit-for-purpose” automotive-grade hardware down the road.
“We use anonymised data that we receive from Yandex.Navigator users, which allows us to understand how to drive in a city with its traffic congestion, accidents, speed limits, road closures and other traffic events,” Isaev said.“We have been using computer vision technologies in a number of our services for quite a while. We use them to find vacant parking spaces or read road signs, for instance, in our geolocation services.”
The video shows the car operating within a driving course of sorts, but testing will open up to public roads within a year, Isaev said.
Check out the demo video below:1 - Reader Likes This Post