Self Driving Cars vs. ‘Shabby’ Roadways
September 8th, 2017|
It is well-accepted that America’s roadway infrastructure is in need of reboot. How will self-driving cars respond to “shabby U.S. roadways,” as they were recently described in a Reuters article.
The author sets the scene: A press event at the Los Angeles Auto Show. Volvo’s semi-autonomous prototype is in the limelight. Things don’t go as planned. The automaker’s CEO loses his cool:
It can’t find the lane markings!” [the CEO] griped to Mayor Eric Garcetti, who was at the wheel. “You need to paint the bloody roads here!”
The article notes that, contrary to other developed countries, in the United States the lack of standardization in road signs and markings makes it difficult for self-driving cars to navigate across state lines.
As explained in the article, autonomous vehicles rely on a number of sensors to “plot their trajectory and avoid accidents.” These sensors include cameras, which take images of the road, radar, sending radio waves that bounce off objects, and “LiDAR,” which emits light pulses that reflect off objects.
These three types of sensors carry distinct advantages and disadvantages. For instance, the camera is only limited to what it can “see,” i.e., what is directly in front of it. It bears to reason that cameras lose effectiveness in inclement weather. Radar can work in all weather but cannot differentiate objects.
While “on a good road in daylight” cameras are sufficient to distinguish different elements of the roadway, “without lane markings, the car needs more technology.”
Thus, a self-driving car reliant on cameras alone would not fare well on a faded or unkempt roadway.
Radar and LiDAR fill this void. These technologies can give self-driving cars their bearings by, for example, “[t]riangulating between trees to the right, boulders to the left, and other vehicles ahead…”
The article explores how recent developments have decreased the cost and size of LiDAR technology:
A host of companies – including Silicon Valley firms Quanergy and Velodyne and international suppliers like Paris-based Valeo – are vying to reduce the cost and size of lidar from the bulky, $75,000 Velodyne version first seen on the roof of Google’s self-driving car. In January, Quanergy unveiled a small $250 Lidar with no moving parts. Automakers want the price to drop below $100 for production vehicles, which Quanergy promises to do by 2018.
The article also explains that “sub-par roads” are fueling efforts by companies, such as TomTom, to create three-dimensional maps that can provide the car’s roadway location “within centimeters.”
It appears that we have the technology to overcome the potholes and faded markers. Will “shabby” roads disrupt the development and introduction of self-driving cars?