Sunday, October 2, 2022

Self-driving cars from Yandex have driven more than six million kilometers in ‘difficult conditions’

Must read


Yandex, The Russian multi-hyphenated internet giant, started testing his autonomous cars on the icy winter roads of Moscow more than three years ago. The goal was to create a “universal” autonomous vehicle that could maneuver safely in different cities around the world. Now Yandex claims its trials have been a resounding success. The vehicles recently reached a milestone by traveling more than 10 million kilometers (over six million miles) in autonomous mode, the majority of the distance covered in the Russian capital.

This is important because Moscow has some of the most difficult weather conditions in the world. In January alone, the city was hit by a Balkan cyclone that blanketed the streets in snow and dropped temperatures to minus 25 degrees Celsius (-13 degrees Fahrenheit). For self-driving cars – which rely on electroluminescent sensors, known as LIDAR, to track the distance between objects – snowfall and condensation can affect visibility.


To overcome the dangerous conditions, Yandex claims to have increased its LIDAR performance by implementing neural networks to filter snow from the lidar point cloud, thereby improving the clarity of objects and obstacles around the vehicle. It also provided the system with historical winter driving data to help it distinguish car exhaust fumes and condensation clouds from heater vents. To top it off, Yandex says neural “filters” can help its vehicles beat human drivers by identifying pedestrians obscured by winter haze.

Driving on Moscow’s roads has also helped improve road navigation technology. The system was able to adapt to both sleet and harsher ice conditions over time, according to Yandex, allowing it to gradually make better decisions on everything from throttling to braking to shifting of track. In addition, winter conditions have caused the tracking technology built into the system to adapt to hazards such as hidden road signs and street limits and snow accumulates “building sizes”. This was made possible by live mapping, motion, position, and motion data measured by the system’s mix of sensors, accelerometers and gyroscopes.

When it launched the Moscow test in 2017, Yandex was among the first to put self-driving cars to the test in a harsh, freezing climate. But soon after, Google followed suit by taking its Waymo project in the snowy streets of Ohio and Michigan.


- Advertisement -spot_img

More articles


Please enter your comment!
Please enter your name here

- Advertisement -spot_img

Latest article