Russia to launch first autonomous tram in Moscow

PC Transport Systems and Cognitive Technologies have partnered to build a fully autonomous tram by 2021-2022.

The Russian manufacturer of urban electric vehicles and European developer of artificial intelligence (AI) for autonomous driving solutions plan to launch the first tram in Moscow.

Within the project, Cognitive Technologies is responsible for development of the autonomous driving system for the tramcar.

Rigid trajectory

The company points out that unlike similar solutions for self-driving cars, the new system for rail transport has several “simplifications” that will allow trams to appear on public roads much earlier.

Chief among them is that trams move along an established and rigidly determined trajectory, and don’t have to manoeuvre or change lanes.

In the next two months autonomous tram tests with an operator in the cabin will be held in closed facilities, and after that tests will be conducted at one of the Moscow tram routes.

According to Cognitive Technologies, the developed autonomous driving system detects vehicles and other trams, traffic lights, pedestrians, tram and bus stops, railway switches and various obstacles.

The tram is also able to stop in front of obstacles, maintain a safe distance from cars ahead, as well as accelerate and stop.

"At the initial stage of the project, the intelligent control system will play a role of an active driving assistant in dangerous situations"

Cognitive’s low level data fusion technology allows the computer vision model to efficiently use all the combined raw data coming from cameras and radars. This integration of data from different devices makes it possible to fill the missing information for better understanding of the current road scene.

Cameras, for example, correctly recognise objects in four-fifths of cases, additional data from radar raises the detection accuracy to 99 per cent and higher.

In addition to AI-based computer vision system, the set of elements for the autonomous tram include: 10- to 20 video cameras (located around the perimeter of the tram) and up to 10 radars. The tram will also use GPS sensors and high-precision cartography will be used along its route.

At the initial stage of the project, the intelligent control system will play a role of an active driving assistant in dangerous situations.

On the next stage, until the corresponding legislative issues will be resolved, an operator will remain in the cabin as ‘back-up’. The presence of an operator in the cabin in the coming years is also necessary from a psychological point of view.

Many passengers are not yet ready to adequately respond to the complete absence of the driver in the tram, Cognitive notes.