How Autonomous Vehicles Could Improve Road Safety
A recent study suggests that autonomous cars can drastically reduce fuel consumption, bottlenecks, and collisions.
Join the DZone community and get the full member experience.Join For Free
There has been significant discussion around the kind of environment that will facilitate the roll-out of autonomous vehicles. For instance, might autonomous cars be capable of operating on the same roads as human-driven cars, and what might this cohabitation mean for our safety?
A recent study suggests that even a few autonomous vehicles on the road can make a significant impact on road safety by reducing, or even eliminating, the stop-and-go driving of human drivers.
“Our experiments show that with as few as 5 percent of vehicles being automated and carefully controlled, we can eliminate stop-and-go waves caused by human driving behavior,” the authors say.
Regulating Traffic Flow
The paper contends that using autonomous vehicles to regulate traffic flow is a major new innovation on the horizon and will probably replace existing methods such as variable speed limits. Before this occurs, however, we need to gain a better understanding of the relationship between autonomous vehicles and human drivers.
The researchers conducted a number of experiments in Tucson, Arizona, whereby autonomous cars circled a track alongside 20 human driven cars. The authors hypothesized that human drivers naturally create stop-and-go traffic, even without bottlenecks or other disruptions, thus creating ‘phantom traffic jams’.
They found that by controlling the pace of the autonomous vehicle, they were able to smooth the flow of traffic for all vehicles on the track. What’s more, the experiment highlighted how just a few of these autonomous vehicles were enough to provide this boost, eliminating waves, and reducing fuel consumption by 40%.
“Before we carried out these experiments, I did not know how straightforward it could be to positively affect the flow of traffic,” the authors say. “I assumed we would need sophisticated control techniques, but what we showed was that controllers which are staples of undergraduate control theory will do the trick.”
Optimistically, the team believes that many of the semi-autonomous technologies already available in vehicles has the potential to provide a similar boost. For instance, adaptive cruise control was found to be effective in smoothing traffic flow even if vehicles with this technology remained relatively low.
“Fully autonomous vehicles in common traffic may be still far away in the future due to many technological, market and policy constraints,” the team says. “However, increased communication among vehicles and increased levels of autonomy in human-driven vehicles is in the near future.”
Suffice to say, it will probably be more challenging to get a few fully autonomous vehicles onto the road than it will to advance from that tipping point and become fully autonomous, but the team is confident that the change will come.
“The proper design of autonomous vehicles requires a profound understanding of the reaction of humans to them,” they say, “and traffic experiments play a crucial role in understanding this interplay of human and robotic agents.”
The researchers next hope to up the ante and explore the impact of autonomous vehicles in much denser traffic with a more complex range of options available to the human drivers. It’s a study that’s well worth keeping tabs on.
Published at DZone with permission of Adi Gaskell, DZone MVB. See the original article here.
Opinions expressed by DZone contributors are their own.