Urban Transport

Autonomous tram to start closed testing ahead of Moscow street debut

The aim of the autonomous tram project is to remove the human factor from tram operation to improve safety
The aim of the autonomous tram project is to remove the human factor from tram operation to improve safety
View 4 Images
The autonomous tram's AI-based vision computer system will be able to detect tram/bus stops, and stop for passengers
1/4
The autonomous tram's AI-based vision computer system will be able to detect tram/bus stops, and stop for passengers
When an obstacle on the track is detected, such as a pedestrian, the autonomous tram will come to a stop a safe distance from the obstacle
2/4
When an obstacle on the track is detected, such as a pedestrian, the autonomous tram will come to a stop a safe distance from the obstacle
The aim of the autonomous tram project is to remove the human factor from tram operation to improve safety
3/4
The aim of the autonomous tram project is to remove the human factor from tram operation to improve safety
The autonomous tram project will start with closed facility testing before moving on to tram route testing in Moscow
4/4
The autonomous tram project will start with closed facility testing before moving on to tram route testing in Moscow

A Russian urban electric vehicle manufacturer and developers of artificial intelligence for autonomous driving systems are working on a city tram that will trundle itself around the streets of Moscow in the near future. The fully autonomous tram is due to start closed facility testing shortly, ahead of street tests along Moscow's tram routes.

The aim of the joint project by PC Transport Systems and Cognitive Technologies is to develop a tram capable of rolling through Moscow districts without a human driver in the cab, "minimizing the number of accidents and reducing their dependence on human factor."

The resulting vehicle will be available to Russian markets and beyond – including Germany and China – by 2021/2022.

The autonomous tram's AI-based vision computer system will be able to detect tram/bus stops, and stop for passengers
The autonomous tram's AI-based vision computer system will be able to detect tram/bus stops, and stop for passengers

The tram's AI vision computer system is supplied with visuals from 10 to 20 cameras positioned around the tram, and data from as many as 10 radar sensors. GPS will help pinpoint its position on "high precision cartography" as it drives itself along the tracks.

"The combination of sensors that includes cameras and radars ensures an accurate and reliable detection of road scene objects in any weather conditions (night, rain, fog, snow, blinding light etc.)," said Olga Uskova of Cognitive Technologies in a press release.

The autonomous tram will be able to detect other vehicles (including trams), traffic lights, pedestrians, tram/bus stops, and switches on the tracks, and respond appropriately. The project team says that the vehicle will come to a halt when obstacles are detected, for example, and will also maintain a safe distance behind cars ahead.

Testing at a closed facility is due to start within the next two months, though the tram won't be going it alone. A human operator will be in the cabin ready to take over if needed. The project will then break out to Moscow's tram routes after that.

Though the aim is to have the tram run autonomously, the project sees human operators remaining in the cabin for some time to come – either until any legislative restrictions are lifted or merely as psychological comfort for passengers, who may not feel at ease in driverless trams.

Source: Cognitive Technologies

1 comment
Martin Winlow
A tram, by definition, can never be 'fully autonomous'!
Thanks for reading our articles. Please consider subscribing to New Atlas Plus.
By doing so you will be supporting independent journalism, plus you will get the benefits of a faster, ad-free experience.