By driving smarter, autonomous cars have the potential to move people in and around cities with far greater efficiency. Their projected energy performance, however, has largely ignored their energy inputs, such as the electricity consumed by brawny on-board computers. First-of-a-kind modeling shows that autonomy’s energy pricetag could be high enough to turn some into net energy losers.
Robotic cars are great at tracking 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.” Bikes are also being left behind by the machine learning techniques that enable detection systems to train themselves by studying thousands of images in which known objects are labeled. Most of the training, to date, has employed images featuring cars, with far fewer bikes. Continue reading “The Self-Driving Car’s Bicycle Problem”