Quantcast

Google’s Self-Driving Car Is Getting Smarter On City Streets

April 29, 2014
Image Credit: Google

Brett Smith for redOrbit.com – Your Universe Online

Cyclists, pedestrians, railroad tracks and other elements can make driving in an urban environment complex and disorienting at times, but according to Google’s Self-Driving Car Project – these potential hazards can be handled in a fairly predictable manner by a computer.

Project director Chris Urmson revealed on Google’s official blog on Monday that his team has been focusing more on adapting self-driving car technology to city streets – more specifically the streets of Mountain View, Calif.

“A mile of city driving is much more complex than a mile of freeway driving, with hundreds of different objects moving according to different rules of the road in a small area,” Urmson wrote. “We’ve improved our software so it can detect hundreds of distinct objects simultaneously—pedestrians, buses, a stop sign held up by a crossing guard, or a cyclist making gestures that indicate a possible turn. A self-driving vehicle can pay attention to all of these things in a way that a human physically can’t—and it never gets tired or distracted.”

The self-driving car team has tested and adapted their technology over the 700,000 autonomous miles the test vehicles have traveled so far. Their latest work revolves around unique driving situations, such as construction areas.

“We’ve taught the vehicle to recognize and navigate through construction zones. Our sensors spot the orange signs and cones early to alert the car of the lane blockage ahead, and we can change lanes safely,” said project test driver Priscilla, in a video released by Google.

In the video, Priscilla narrates several scenes involving the self-driving car’s decision-making process as depicted by both ‘live’ video and computer animation – complete with animated, colored boxes to show how the cars’ computers tracks various objects. Driving situations shown in the video include crossing railroad tracks and moving alongside a cyclist.

“Our cars treat cyclists as a special category of moving object,” Priscilla said. “When the cyclist holds up his arm – our software detects the hand signal and predicts his movement into our lane. The car knows to continue yielding to the cyclist passing by, even when he changes his mind – multiple times.”

According to Urmson, the team’s next goal is to see how the driving system can handle even more roads in Google’s hometown of Mountain View. After that, the team plans to move on to roads in a different town.

“We still have more work to do, but it’s fun to see how many situations we can now handle smoothly and naturally,” Priscilla noted at the end of the video.

The latest update from the Self-Driving Car Project comes about 18 months after the last update, which revealed the test vehicles had traveled more than 300,000 miles.

“This is an important milestone, as it brings this technology one step closer to every commuter,” Urmson wrote at the time. “One day we hope this capability will enable people to be more productive in their cars. For now, our team members will remain in the driver’s seats and will take back control if needed.”

“With each breakthrough we feel more optimistic about delivering this technology to people and dramatically improving their driving experience,” he added. “We’ll see you on the road!”


Source: Brett Smith for redOrbit.com - Your Universe Online



comments powered by Disqus