TMCnet - World's Largest Communications and Technology Community



Under the Hood with Google's Self-Driving Cars

TMCnet Feature

April 28, 2014

Under the Hood with Google's Self-Driving Cars

By Matt Paulson
TMCnet Contributing Writer

For some time now, Google (News - Alert) has deployed a small fleet of self-driving cars, a concept which could become commonplace in the wake of the upcoming 'Internet of Things' environment where Internet connections are used in almost every device and appliance. Between using the Internet to navigate directions from point A to point B and a wide array of lasers, cameras, radar and a host of other sensors to get a clear picture of what's on the road, the self-driving cars are already reporting amazing results. Google announced back in 2012 that the technology would be publicly available within five years, and it appears that Google is on the right track to deliver on that promise, despite minor roadblocks.

As of now, Google has only operated the cars on freeways, which are much easier to navigate than city streets and offer fewer anomalies like pedestrians and cyclists. Google recently announced its Lexus RX450H SUVs autonomously completed a total of around 700,000 accident-free miles, with a human driver only sitting behind the wheel to take over in the event of an emergency. This distance is equivalent to driving in a continuous line and circling the globe more than 28 times.

Of course, before Google unleashes the technology onto public city streets, improvements need to be made in the way the cars change lanes and merge into traffic. The cars also need to reliably know when to safely turn right at a red light, determine who should go first at a four-way stop signs as well as being prepared for driving in inclement weather.

Regardless, Google is still doing testing in its home town of Mountain View, California, where Google Maps has already done extensive detail work. Here, the cars already have a very good idea of what the static elements of the roads are, like stop signs—which the cars are able to read, instead of rely on navigational knowledge of where they are. This will allow the cars to keep a sharp eye out for the moving parts – including other cars, cyclists and pedestrians.

Edited by Maurice Nagle

View all articles

Comments powered by Disqus

Technology Marketing Corporation

35 Nutmeg Drive Suite 340, Trumbull, Connecticut 06611 USA
Ph: 800-243-6002, 203-852-6800
Fx: 203-866-3326

General comments:
Comments about this site:


© 2018 Technology Marketing Corporation. All rights reserved | Privacy Policy