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”
Paris threw open nearly one thousand one-way streets to two-way traffic this week — that is, for travelers willing to pedal. Whereas other cities such as Boulder and London have created a handful of designated counterflow bike lanes, the new rules taking effect in Paris this week allow bicyclists to cycle upstream against automobile traffic within all of the city’s 30 kilometer-per-hour zones.
Generally speaking these 30-kph zones comprise knots of narrow streets serving primarily neighborhood traffic. But Paris city hall expects a big impact for cyclists. According to Paris planners the move will expand route options for cyclists and may also (seemingly against all odds) improve safety. The mayor’s office notes that on some streets cyclists heading upstream will be further from parked cars, minimizing their risk of ‘winning a door prize’ from innattentive automobile users stepping out onto the roadway. Continue reading “Paris Puts the Bicyclette First”