You're a terrible driver. Yes, you. Terrible. At least, you're terrible compared to a robot, which is smarter, faster, and more experienced. In fact, if we all just give up driving on highways and let robots take over for us, we could effectively end highway congestion as we know it by boosting the capacity of our existing roads by a staggering 273%.
On a highway filled to capacity by human drivers (which is about 2,200 vehicles per hour per lane), about five percent of the available road space is taken up by cars. Five percent. This is because humans are so bad at driving that we need lanes that are twice the size of our cars, and at highway speeds, we have to keep between 40 and 50 meters away from the car in front of us.
Researchers at Colombia University took a look at what would happen if we started relying on autonomous or semi-autonomous cars equipped with sensors and/or intervehicular communications systems, and the increase in efficiency is fairly incredible, simply due to the fact that cars can safely travel closer together. When traveling at 100 kph, if all vehicles on the road are simply equipped with adaptive cruise control, highway capacity can safely increase by a factor of 1.4. And if all vehicles on the road are equipped with both adaptive cruise sensors and communication, capacity can be increased by a factor of 3.7. And this increase is without any infrastructure modification: it's purely from making our cars smarter with technology that is commercially available today.
So, with 100% communicating vehicles, you'll get 12,000 vehicles per hour zipping along at 120 kph within about 6 meters of each other. Not too shabby, right? Of course, you have to keep in mind that we'll likely to be limited by the percentage of adoption of these technologies, as illustrated in these graphs:
We may not notice the difference right away, but as more and more cars being to implement sensors and communication, the overall benefits will increase drastically.
Decreasing highway congestion is great, and we're all for that. But, it's really one of the more minor benefits of partially or fully autonomous vehicles. Benefit number one is obvious: a car that's equipped wit a bunch of sensors and that knows what all the other cars around it are doing is a much safer place to be than a car driven by a human. I don't care how good of a driver you are (or you think you are): your car, being for all practical purposes a robot, can digest a huge amount of data and make a decision about the best course of action to take in approximately the same amount of time it takes for you to move your foot from the gas to the brake. Our brains just don't work fast enough to keep up, and if something goes wrong, your car will be vastly better than you are at keeping you (and your passengers) from harm.
The other big benefit that we're looking forward to is the opportunity to not have to drive anymore, or at least, not have to pay attention while driving. A car that drives itself (at least on the highway) would give us the chance to be productive instead of wasting our lives going from Point A to Point B and then back five days a week. Plus, robot cars never get distracted, never get tired, never talk on the phone, never spill coffee on themselves, and don't care in the least about how attractive the person is in the car alongside. The fact is, robots have the potential to be the ideal chauffeurs for all of us.
Every time we talk about robot cars we have to mention two things. Thing One is that all of the technology to do this stuff already exists. And not just in Google's fully autonomous cars: there are cars that you can buy today that have adaptive cruise control that can sense the cars in front of them, blind spot sensors that can see cars to the side, and lane sensors that can track lane markings. Vehicle to vehicle communication is nearly a reality too, and the technology has been successfully demonstrated in Europe in the form of road trains.
Thing Two is that the world just isn't ready for robot cars. The government has no idea how to manage them, and manufacturers are understandably concerned about liability. Here, though, things have started to move a little bit, with first Nevada and now California passing legislation governing their testing and use. This isn't going to be a fast transition, but when it happens, it'll be one of the biggest transportation revolutions since the invention of, let's say, walking.
Highway Capacity Benefits from Using Vehicle-to-Vehicle Communication and Sensors for Collision Avoidance, by Patcharinee Tientrakool, Ya-Chi Ho, and Nicholas F. Maxemchuk from Columbia University, was presented last year at the IEEE Vehicular Technology Conference.
Via [ NBF ]
Evan Ackerman is a senior editor at IEEE Spectrum. Since 2007, he has written over 6,000 articles on robotics and technology. He has a degree in Martian geology and is excellent at playing bagpipes.