FYI.

This story is over 5 years old.

Tech

How AI That Mimics Flocking Birds Could Help Hybrid Cars Run Greener

Researchers have developed an evolutionary algorithm that could reduce fuel consumption in plug-in hybrid electric cars by one-third.

Hybrid cars have long been hailed as a more eco-friendly vehicle option, and researchers are trying to make future hybrids even greener.

The answer potentially lies in helping cars learn their own habits and letting them adjust fuel sources on their own. Engineers from the University of California, Riverside have developed an algorithm they believe can be used in the computers of plug-in hybrid electric cars to reduce their fuel consumption by one-third, according to a study published this week in IEEE Transactions on Intelligent Transportation Systems.

Advertisement

The researchers used evolutionary algorithms based on flocking birds and swarming bees to help plug-in hybrid cars learn about the complexities of zipping around roads and highways. The idea is that the algorithm would allow the car to learn how to optimize energy efficiency based on individual driving history, as well as allow it to share that data with other cars online in its network.

While this study isn't on the level of self-driving cars, vehicular science is one of the cutting-edge fields of the past few years. Between Google's self-driving cars and Tesla's all-electric models, the field is heating up with new inventions.

Plug-in hybrid electric cars usually run on stored electricity from battery packs and then default to fuel. But that method is notoriously inefficient, the study states, and it uses much less electricity to use battery power at various, more opportune times during the trip depending on the speed and other factors.

Read more: Why Electric Cars Are Ditching AM Radio

But switching back and forth between gas and battery power is difficult, and most hybrid cars don't have the tech to make that happen. UCR researchers came up with an algorithm that they believe should make this system much easier.

"By mathematically modeling the energy saving processes that occur in nature, scientists have created algorithms that can be used to solve optimization problems in engineering," study author Xuewei Qi, a postdoctoral researcher at the Center for Environmental Research and Technology in UCR's Bourns College of Engineering said in a release. "We combined this approach with connected vehicle technology to achieve energy savings of more than 30 percent. We achieved this by considering the charging opportunities during the trip—something that is not possible with existing EMS (energy management systems)."

Researchers hope the algorithm could also decrease the amount of greenhouse gases cars emit. In other words, math inspired by nature could help us protect our natural resources. And that is pretty damn cool.

Get six of our favorite Motherboard stories every day by signing up for our newsletter.