Archives January 2018

Autonomous Car Testing in Moscow Is Hard & Necessary

Autonomous Car Testing in Moscow Is Hard & Necessary

Published on THECONNECTEDCAR.COM
Link to publication

What is the worst confluence of driving conditions you can possibly imagine?

It’s probably nighttime in a densely populated city. There would be a vision-obscuring blizzard making the roads slick and unreliable. Traffic would be thick and moving irregularly. Worse, the drivers around you would have seemingly little regard for your safety, or even their own. Even the road signs would be difficult to see.

Welcome to life for drivers in Moscow.

Poorly laid out roads, bad weather and not-so-cautious driving practices make for dangerous automobile treks in the Russian capital. Moscow streets are home to 20 serious car accidents per day, and the road fatality rate in Russia is double that of the United States.

Not surprisingly, that makes it a difficult landscape for autonomous vehicles to navigate. But the conditions in Russia are not all that different from other countries in the world, which is why autonomous developers believe that, with apologies to New York, “if they can make it there, they can make it anywhere.”

At a three-day hackathon in Moscow, engineering students from around the globe and corporate sponsors like Nvidia and Uber gathered to take a crack at developing autonomous systems for Moscow’s roads.

“The event had another purpose: to advance a credo that when it comes to autonomous cars, tougher conditions produce smarter technology,” writes Gaus. “Lidar — the expensive, light-pulsing sensors relied upon by current autonomous car models — is worthless in snow … Instead, cars should be trained to operate using high-definition cameras, low-cost radars and powerful AI that mimics the human brain.”

The idea that Lidar is “worthless in snow,” advanced by Olga Uskova of Russian AV software developer Cognitive Technologies may be an extreme position — nearly all driverless car manufacturers incorporate Lidar sensors in some form.

Nevertheless, Lidar does not work as effectively in the snow, and developers have relied more heavily on other hardware to navigate in adverse conditions. An autonomous vehicle in Finland primarily used radar sensors to complete a journey through a wintry mix.

As for the hackathon engineers in Moscow, cobbling together an autonomous driving system over the course of three sleepless days proved difficult. The top team only managed to achieve 40% accuracy in identifying road signs. The expected culprits were to blame for the difficulties: Snow-covered road signs were difficult for systems to detect, and non-Russian speakers had an even more challenging time differentiating between similar looking road signs.

While success proved elusive at the hackathon, in some ways, that was beside the point.

The fact that driverless car developers are moving beyond building cars that can work in the idealistic sunny climates of Arizona and California and shifting to the more challenging task of creating vehicles that can work in more realistic scenarios is an important sign of progress.

Many expect that self-driving cars will eventually operate 24/7, but they will only be able to do that if they can handle the weather and unique road conditions that present themselves at every moment of the day all over the world.

Published on INVERSE Link to publication

Published on INVERSE Link to publication

Published on INVERSE.COM
Link to publication

Cognitive Technologies has a big plan.

Russia’s first and largest autonomous car project is about to reach the United States. At the Consumer Electronics Show in Las Vegas next week, Cognitive Technologies will demonstrate a self-driving car system that’s primed for the world’s roughest roads and runs on standard computer hardware.

As the company’s president tells Inverse, it’s the culmination of a journey sparked by the success of a chess computer, fueled by a desire to reduce road deaths, and hampered by American visa issues.

The company has an impressive resumé. Founded in 1993 by the guys who created the world’s first computer chess champion, Cognitive Technologies worked on technologies including image and voice recognition, and in the past has worked with big names like Intel and Yandex. In 2014, the Cognitive Pilot program was set up to apply the company’s talents to autonomous driving.

“The whole project was built to design the autopilot for real roads, Russian roads,” Roman Tarasov, the company’s VP for global business, told Inverse in March 2017. “Most of the roads on the planet are like this. So lack of light, snow, fog, bad road marks.”

Watch the company test its autonomous driving system on the roads in November 2017.

As Waymo, Tesla and Uber battle it out in Silicon Valley, Cognitive has quietly moved from strength to strength. It’s hosted a hackathon with students from MIT, Cambridge and Peking University. It’s developed assistive driving technologies for Russian trucking giant Kamaz, with a view to developing a fully autonomous truck by 2020. The team has moved some of its operations to Amsterdam, while research continues in Moscow. CES is the next big step.

Inverse spoke with Olga Uskova, president and founder of Cognitive Technologies and developer of Cognitive Pilot, to find out more about the big moment.

How are you feeling about the big CES moment for your company? Nervous? Excited?

It’s a first run, a premiere for us. It will be Cognitive Technologies’ first time at CES. Of course we worry. We will present a number of completely new technologies that we have never demonstrated before at any other event. And of course we are naturally worried about the reaction of specialists who come to CES from all over the world.

How many people are going from the company, who is representing Cognitive?

Unfortunately, some negative visa issues that arose recently between our countries made it impossible for half of the announced team members to arrive to the U.S., but key specialists will be at CES. For example, everyone will be able to chat at the booth with the CTO of the company.

We believe that CES is the quintessential show of all consumer wishes and desires for the upcoming year. New trends, latest releases, brand wars, newcomers and outsiders – all will be there. A lot becomes clear after you study the list of participants and their contribution to the world’s economy.

What message do you want to give to people?

We can and we must save millions of people who die on the roads around the world. The official statistics show more than 1.3 million deaths per year. Our technologies can already reduce this horrible figure by 44 percent, so several hundred thousand people will remain alive if these technologies will be promptly implemented.

My academic supervisor died in 1993 in a terrible car accident. After a car accident in 1997, I personally experienced seven operations on my face. Almost every family in the world has something to remember on this terrible topic. It seems to me that there will be nothing more important at CES than our booth.

Do you expect a lot of skepticism from people more familiar with big names like Waymo?

No, I don’t. The new markets in the automotive sphere are still forming at the moment. Only fools will wrinkle their noses at the sight of the new names. In reality everyone is looking for fresh solutions and new breakthrough technologies. The markets of neural systems developers, vision systems manufacturers, manufacturers of autonomous cars — these are still very young and exclusive. They now require some serious scientific and financial investments. Therefore, there is an increased attention of serious experts to such companies as ours. For us it is a very big responsibility.

Have you had any interest from CES attendees already?

Of course we’ve been preparing for this exhibition and in advance we have arranged a number of meetings with some partners we are interested in. We are waiting for innovations in the fields of microprocessors and video cameras, and also in the fields of Internet of Things and connected cars. We are very interested in the joint work, because this is the only way we can offer an ideal product for a modern customer, a user of an autonomous vehicle.

Will you be demonstrating the tech at CES? How is the booth set up?

Our mission is to show real technologies that can work in real time on real roads. We are bringing from Moscow technologies that are not afraid of snow, mud and impassibility of roads. Google is doing fine on the dry and sunny roads of California. Cognitive Technologies will represent on CES the technology for the remaining 98 percent of the world’s roads. At our booth you will be able to see a live demonstration of the technology working on snowy roads, in a storm and in a thunderstorm, with interrupted or hidden-under-the-snow markings. A special show will be organized for farmers. We will also present a separate recognition of small details of cars – headlights, mirrors, car plates etc.

We will also present our global trend for 2018 – the concept of Low Level Data Fusion. This is our technology that combines data from several operating systems and sensors: neural networks, data from high resolution image radars and cameras.

This technology allows the computer vision model to efficiently use all the combined data coming from various sensors to the computing unit. Basically, information taken from each of the sensors is synchronized and reduced to one single coordinate system. The “raw” data goes to computer, where it is processed, and then materials from cameras and radars mutually enrich each other.

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 recognize objects in 80 percent of cases, additional data from radar raises the detection accuracy to 99 percent and higher.

Complex use of all data allows to combine information about the speed, type of the object and distance to it, its location and physical characteristics. The implementation of this Fusion technology alone will reduce the accident rate of autonomous vehicles up to 25 percent.

What do you hope to see at CES from others, are you looking for any opportunities?

At CES we are looking forward to seeing some compact and productive information processing solutions that could be placed on the vehicles. We also want to see new solutions for car cameras that will help us improve the quality of our system on the roads. Basically, we are interested in any systems that will ensure a comfortable stay for the passenger and a driver during the autonomous driving in a traffic jam. We also hope to perhaps see something completely new, something that we couldn’t even imagine has already been created. From CES you always expect a miracle!

Moscow Is Not the Ideal Place to Develop Self-Driving Cars, Russian Firms Say

Moscow Is Not the Ideal Place to Develop Self-Driving Cars, Russian Firms Say

Published on THEDRIVE.COM
Link to publication

Developers of self-driving cars in the United States are lucky that Silicon Valley is the home of the U.S. tech industry. California’s sunny weather and well-maintained roads make it a good testing ground. That can’t be said of Moscow.

The Russian capital is challenging even for human drivers, but local companies are testing self-driving cars there anyway, according to a recent report by The Guardian. Poor weather, including snow that obscures traffic signs, bad roads, and aggressive, unpredictable drivers make Moscow a self-driving car hell.

Cars developed in less-harsh environments can’t possibly function in Moscow, Olga Uskova of Cognitive Technologies, a Russian software company, told The Guardian. Indeed, at a recent hackathon for self-driving cars, international competitors found the data from Russian roads to be inadequate. Snow often obscured traffic signs, which non-Russians said tend to be hard to tell apart anyway. A Russian team won the competition by digging into the trove of local dash-cam footage that has also become a staple of YouTube.

Russian drivers feel the need to equip their cars with dash cams because crashes are common. Traffic laws are widely ignored in Moscow, where speeding violations only lead to a $4 fine, paid over the phone. There are nearly 20 serious crashes a day in the city.

But for now, the biggest hurdle for autonomous cars in Russia may be regulatory. Russia has no formal regulations sanctioning the test of self-driving cars on public roads. The only designated autonomous-car testing area in Moscow is a 400-meter (1,312-foot) track sprinkled with traffic signs and pedestrian crossings to simulate a real street. Test cars will need to rack up some real-world mileage eventually.

If self-driving cars are allowed onto the streets of Moscow in large numbers, the city could become an important crucible for the technology. Like Indian cities or even New York City, the challenging environment will push the limits of self-driving cars. If these cars can handle Moscow, they can probably handle anything.

Testing Autonomous Cars In Russia Will Be Hell But It's The Reality Of The Situation

Testing Autonomous Cars In Russia Will Be Hell But It’s The Reality Of The Situation

Published on JALOPNIK.COM
Link to publication

The majority of self-driving tech testing is happening on the pristine streets of sunny California, but across the Pacific, autonomous tech developers in Russia are also working to make robot cars a reality. But in the hellish driving environments found in Moscow, that’s not an easy feat, as a fascinating story from The Guardian recounts.

Silicon Valley, for one thing, offers clear weather and well-maintained roadways. In Russia, where testing is allowed in very limited circumstances right now, that won’t be the case. From The Guardian:

” says Olga Uskova of Cognitive Technologies, a Russian software maker that specializes in autonomous vehicles. “The environment is ever-changing: the snow has covered traffic signs; it’s raining on your windshield, the sun is blocking you. Our people train using these kinds of data.”

Uskova asserts that technology tested in sun-drenched utopias can’t possibly translate to a city like Moscow. Gnarly road planning, terrible weather and reckless habits make the Russian capital one of the worst cities in the world for drivers.

Uskova isn’t wrong. Some automakers have lately taken to testing autonomous cars in cities that regularly face inclement weather, like Detroit, but for the most part, the development has been centered around Silicon Valley. That can’t last if autonomous cars are ever going to catch on.

So the insight from Russia is worth taking into consideration. Here’s more from The Guardian:

With roads that spread like a cobweb away from the Kremlin, disturbances like car wrecks, construction and government motorcades can wreak havoc for miles. Seat belts are scorned, and traffic laws widely ignored; speeding violations are enforced with $4 fines, paid by phone. It’s no surprise that Russia’s rate of road fatalities is nearly double that of the US, with an average of 20 serious accidents a day just in Moscow. Or, for that matter, that dashcam videos of Russian road fights and collisions make up such a popular subgenre on YouTube.

The Guardian visited a three-day “hackathon” event for driverless cars, and found that one common issue for driverless cars—signs—tripped up some of the engineers in attendance.

Most cars struggled to identify signs, for instance, which were hard to detect in snow or rain; and for non-Russian speakers, the task was practically impossible.

“The problem is that the signs are small, and in Russia they look very similar,” explained Sami Mian, a computer scientist at Arizona State University. “The main difference is numbers and arrows, and a city entry sign can look almost the same as a stop sign. The top team had 40% accuracy.”

The story notes that car testing is limited in Moscow to a quarter-mile track outfitted with pedestrian crossings, road signs and a roundabout, so there’s still a ways to go before testing expands. But it offers relevant context for the auto industry: it’s going to be a slow crawl to expand autonomous driving across the world.

Moscow is a terrifying city for drivers. So what if a car doesn't have one?

Moscow is a terrifying city for drivers. So what if a car doesn’t have one?

Published on TheGUARDIAN.COM
Link to publication

Chaotic roads, bad weather and reckless habits make the Russian capital one of the worst to drive, and its quest to build an autonomous car uniquely challenging.

In certain sunny climes, self-driving cars are multiplying. Dressed in signature spinning sensors, the vehicles putter along roads in California, Arizona and Nevada, hoovering up data that will one day make them smart enough to run without humans.

Besides perennial sunshine, those places share other common traits: wide, well-manicured roads, functional traffic enforcement, and agreeable local governments. That’s how Chandler, Arizona – a Phoenix suburb on nobody’s radar as of a few weeks ago – became the first US town to host autonomous cars on public streets without human safety drivers. Courtesy of Waymo, they’re expected to start carrying passengers within the next few months.

If you ask many Silicon Valley companies, the future of driverless cars is just a couple of years away. But halfway across the world, the outlook is a lot more skeptical.

“We don’t have the luxury of California roads,” says Olga Uskova of Cognitive Technologies, a Russian software maker that specializes in autonomous vehicles. “The environment is ever-changing: the snow has covered traffic signs; it’s raining on your windshield, the sun is blocking you. Our people train using these kinds of data.”

Uskova asserts that technology tested in sun-drenched utopias can’t possibly translate to a city like Moscow. Gnarly road planning, terrible weather and reckless habits make the Russian capital one of the worst cities in the world for drivers.

With roads that spread like a cobweb away from the Kremlin, disturbances like car wrecks, construction and government motorcades can wreak havoc for miles. Seat belts are scorned, and traffic laws widely ignored; speeding violations are enforced with $4 fines, paid by phone. It’s no surprise that Russia’s rate of road fatalities is nearly double that of the US, with an average of 20 serious accidents a day just in Moscow. Or, for that matter, that dashcam videos of Russian road fights and collisions make up such a popular subgenre on YouTube.

But most of the world’s roads look more like Russia than Mountain View, and according to Uskova, that gives Russian developers an edge in building the brains of autonomous cars.

That theory was tested at a recent event in Moscow, advertised as the world’s first hackathon for driverless cars. In an austere, Soviet-era dormitory bedecked with Steve Jobs and Elon Musk posters, top engineering students from far-flung schools like MIT, Cambridge and Peking University sank into beanbag chairs for a three-day coding binge.

“We’re here because it’s a chance to change the world over the next 10 to 15 years,” said Mitch Mueller, a student who traveled from the University of Wisconsin to compete. They were also competing for a cash prize, bragging rights and – most importantly – the attention of participating companies, including Uber and Nvidia, eager to recruit the next generation of AI talent.

The event had another purpose: to advance a credo that when it comes to autonomous cars, tougher conditions produce smarter technology. Lidar – the expensive, light-pulsing sensors relied upon by current autonomous car models – is worthless in snow and thus “a fake”, says Uskova. Instead, cars should be trained to operate using high-definition cameras, low-cost radars and powerful AI that mimics the human brain.

As the 150 engineers pored over Moscow road data, it was obvious that this vision is a long ways off. Most cars struggled to identify signs, for instance, which were hard to detect in snow or rain; and for non-Russian speakers, the task was practically impossible.

“The problem is that the signs are small, and in Russia they look very similar,” explained Sami Mian, a computer scientist at Arizona State University. “The main difference is numbers and arrows, and a city entry sign can look almost the same as a stop sign. The top team had 40% accuracy.”

That team, three local guys from Moscow, had tapped into a secret weapon: a trove of the popular dashcam footage, which had been harvested and stored at nearby Moscow State University. Derived from 100,000 dashcam videos, that data served as the building blocks of a basic neural network hammered out by the cigarette-puffing coders, who mentioned that they had slept a total of five hours over three days.

Russian-built autonomous systems are already in use by Kamaz, Russia’s largest truck maker, and an agricultural equipment company. Both are working with Cognitive Technologies to build autonomous machines. But adapting the technology for city use, and bringing it to the international stage, is a steep battle.

No government agency has developed regulations for autonomous cars, so road testing is constrained to designated testing zones. The only car testing zone in Moscow is a 400m track embellished with pedestrian crossings, road signs, markings and a section with circular traffic. It’s a lousy facsimile of Moscow roads, or any road. But even worse is its location far outside the city center: a planned ride-along was scrapped because of bad traffic.