As much as we’re looking forward to cars with autonomous features, adding autonomy to trucks is at least as valuable, if not more valuable, considering how much time trucks (and the humans in charge of them) spend on the roads.
Volvo, which has been experimenting with autonomous vehicles for quite a while, has a goal of making its trucks (and cars) accident free, and it’s working on a project that combines cameras, radars, and other sensors to create a predictive 360 degree view of things that Volvos should probably try and avoid running into.
This sort of predictive tracking is something that Google uses on its autonomous cars as well, and it’s especially important for tracking people (as opposed to other vehicles), since neither pedestrians nor bicyclists can be reliably expected to follow rules around roads, whether those rules are legal ones or just basic common sense. And while prediction is all well and good, a system that makes decisions based on what it thinks a person on a bike is likely to do also must be prepared to react to that person doing something incredibly idiotic.
The key to the safety here isn’t really the driver alert aspect: it’s the fact that the truck can take over completely and engage the brakes or steering when necessary. Alterting the driver is fine, but taking the human out of the loop completely is much more effective. Humans really need to start accepting the fact that most of us are terrible drivers, and that the only reason we do as well as we do is that most of the time we don’t really have to pay attention because nothing unexpected happens. Computers, though, pay attention all the time, and never get sleepy or bored or angry or distracted, which is why we want to them to, at the very least, be watching our backs (and sides and fronts) whenever possible.
Volvo says that this system will be ready for the market in “five to ten years time,” which is usually code for “we have no freakin’ idea.” This seems awfully pessimistic, but it’s partly because a truck’s weight (and often size) can vary widely over the course of a day, which makes autonomous avoidance maneuvers more difficult to reliably plan. However, since Volvo says that all of the components are in place and that it’s just a matter of testing, I’d be willing to guess that we’ll be seeing tech like this starting to become available in 3-5 years at the most.
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.