SPECTRUM: Exposing the Power Vampires in Self-Driving Cars

800px-Waymo_Chrysler_Pacifica_in_Los_Altos,_2017

Drag from rooftop sensors makes Waymo’s self-driving minivan an energy hog. Photo: Wikimedia/Dllu

By driving smarter, autonomous cars have the potential to move people around and between cities with far greater efficiency. Estimates of their energy dividends, however, have largely ignored autonomous driving’s energy inputs, such as the electricity consumed by brawny on-board computers.

 

First-of-a-kind modeling published today by University of Michigan and Ford Motor researchers shows that autonomy’s energy pricetag is substantial — high enough to turn some autonomous cars into net energy losers.

“We knew there was going to be a tradeoff in terms of the energy and greenhouse gas emissions associated with the equipment and the benefits gained from operational efficiency. I was surprised that it was so significant,” says to Greg Keoleian, senior author on the paper published today in the journal Environmental Science & Technology and director of the University of Michigan Center for Sustainable Systems. Continue reading

Advertisements

The Self-Driving Car’s Bicycle Problem

6210901187_dc5fc87af0_b

Human error plays a role in 94% of U.S. traffic fatalities. Image: William Murphy via Flickr

Robotic cars are great at monitoring other cars, and they’re getting better at noticing pedestrians, squirrels, and birds. The main challenge, though, is posed by the lightest, quietest, swerviest vehicles on the road.

“Bicycles are probably the most difficult detection problem that autonomous vehicle systems face,” says UC Berkeley research engineer Steven Shladover.

Nuno Vasconcelos, a visual computing expert at the University of California, San Diego, says bikes pose a complex detection problem because they are relatively small, fast and heterogenous. “A car is basically a big block of stuff. A bicycle has much less mass and also there can be more variation in appearance — there are more shapes and colors and people hang stuff on them.”

That’s why the detection rate for cars has outstripped that for bicycles in recent years. Most of the improvement has come from techniques whereby systems train themselves by studying thousands of images in which known objects are labeled. One reason for this is that most of the training has concentrated on images featuring cars, with far fewer bikes. Continue reading