A Robo-Car Just Drove Across the Country
Press2ToContinue writes with this news from Wired: Nine days after leaving San Francisco, a blue car packed with tech from a company you've probably never heard of rolled into New York City after crossing 15 states and 3,400 miles to make history. The car did 99 percent of the driving on its own, yielding to the carbon-based life form behind the wheel only when it was time to leave the highway and hit city streets. This amazing feat, by the automotive supplier Delphi, underscores the great leaps this technology has taken in recent years, and just how close it is to becoming a part of our lives. Yes, many regulatory and legislative questions must be answered, and it remains to be seen whether consumers are ready to cede control of their cars, but the hardware is, without doubt, up to the task."
That last one percent is a bear, though.
I wonder what long distance truck drivers are thinking right about now.
I come here for the love
CMU had a car drive itself across America in 1995, 98% autonomously:
http://www.cs.cmu.edu/~tjochem/nhaa/Journal.html
Lane following is one of the simplest things for vehicle technology to do. All it does is follows the lane lines and keeps a speed/ or minimum distance from the vehicle in front. I bet every time they had to change highways the driver took over. Also notice it was not raining heavily, snowing or recently snowed in the trip. Current technology has problems in those cases. Comparing lane following to autonomous driving is like comparing algebra to calculus.
Most humans drive fine in 'conditions they're already prepared for'. It's the other fraction of one percent where most of the accidents happen.
IF, and that's a big pessimistic if, eventually autonomous car is deemed unable to navigate local city streets, then what you will see are large parking lots springing up around highway exits, where robo-cars will park itself when it leaves the highway.
There, either the human driver takes over immediately and go away, or more likely, the car alert the sleeping driver to wake up. The driver, after sleeping all the way since he got on the highway, gets off and have a meal and refresh himself, then drove off.
OR, the passengers don't even know how to drive. Some other driver drove to the lot next the highway, get off, the car take over to get on the highway, reach the lot near destination, and some other driver came and drive the car to the destination. Think kids of divorced parent, or kids going to visit grandparents.
Same approach applies much more easily to trucks. Now truck drivers only need to go round and round between the last leg on both sides, letting the truck drive itself over the long haul. That means cheap transport, no need for long tiring trips away from home, and fewer accidents.
JUST automating the highway portion is going to give huge benefits, there is no need over worry about the last 1% of the trip.
Oliver.
Most drivers accidents are in places they are familiar with. Its not entirely clear if this is simply due to mostly driving in such places, but it is commonly asserted that over familiarity often leads to inattention. I know this is true for me, and so presumably for many others. The fact remains, human drivers have a high error rate, and so far all the automated driving systems being tested in the US fall far below that number, even given that they drive in controlled circumstances.
"Malo periculosam, libertatem quam quietam servitutem." -- Jefferson
Fit the truck with two way communications and let a remote operator in a remote location take over. One driver could service 10 or more trucks, driving only last-mile areas.
Is it just my observation, or are there way too many stupid people in the world?