The Industry's #1 Resource




WNCN -- Ever since Henry Ford strapped on four wheels to the base of the Model T back in 1908, society has fostered a growing question: When will we be able to get behind the wheel of a self-driving car?

Cartoons as far back as the 1950’s predicted we would be zipping around in futuristic self-driving cars by the year 2000. Unfortunately, it’s taking us a little longer than that.

But the future of transportation may be closer than you think. A new research project at the University of North Carolina’s Computer Science Department is looking to bridge the gap between fantasy and reality.

“Folks may look back at us today and wonder, ‘Why did these people ever try to drive these cars themselves?’” said Dr. Jim Anderson, a professor at UNC and the principal investigator on the project.

Anderson and his team have partnered with General Motors to create data for a more reliable, safer and cheaper autonomous car.

“General Motors gave us some funding and then together we went and got some additional funding from the National Science Foundation. As a result of these two things, this grew into a fairly large project,” said Anderson

The team was able to secure $300,000 in funding from General Motors and $1 million from the National Science Foundation.

Anderson and his team of four faculty members and four graduate students began breaking down the code; trying to figure out how to fit more computing power in a car in a realistic setting.

“It sucks up a lot of size, weight and power which are important concerns,” Anderson said. “This gets very expensive, very fast.”

The team’s goal is to give an autonomous car the reliability of a human’s split-second thinking.

“If you think about the amount of information that comes to the human brain, the vast majority of it is visual information and a big chunk of our brain is dedicated to this,” said Dr. Alexander Berg, a professor at UNC also working on the project. “These are indications that this is a challenging task.”

Google has also been experimenting with self-driving cars since 2009. Since then, the cars have driven 1.8 million miles and have been involved in several accidents.

However, Google says all of those accidents were a result of human error, but more research is needed.

“I’ve seen estimates on the cost of the hardware of Google self-driving cars being $150,000 and that’s significantly more expensive than most of the cars I’d ever think about buying anyway,” said Berg.

Read the rest of the story here: http://wncn.com/2015/07/08/unc-explores-future-of-transportation/

The Magazine

Magazine Quick Links







Copyright - Mobile Electronics Association 2020