Can Algorithms Design Safer Intersections?

Eventually, maybe, but we already know how to redesign streets to save lives.

The red areas mark close calls between drivers and pedestrians. Image via City of Bellevue
The red areas mark close calls between drivers and pedestrians. Image via City of Bellevue

Cities and tech firms are deploying new technology to gauge risks at dangerous intersections. These sensors, cameras, and machine-learning algorithms are promising, especially when it comes to measuring close calls that don’t result in crashes — but the applications of this information are still getting fleshed out. In the meantime, there’s no reason to wait on designing safe streets.

Since March, sensors and cameras have been deployed at the intersection of Massachusetts Avenue and Beacon Street in Boston, a dangerous crossing where volunteers installed pop-up safety improvements after a cyclist was killed by a driver in 2015.

The monitoring equipment is part of a partnership between Verizon and the city of Boston announced last year, reports Elizabeth Woyke at MIT Technology Review:

Verizon outfitted the intersection with 50 cameras and sensors, including “quad cameras” — each containing four smaller cameras that can pan, tilt, and zoom in different directions — and infrared cameras that can do thermal imaging, which is useful for discerning traffic activity in snow and rain. Below ground, Verizon installed dozens of magnetometer sensors that detect the velocity, number, and size of passing cars, trucks, and buses by registering a change in frequency when large metal objects move over them. Since most bikes don’t have enough conductive material to trigger the magnetometers, the site also has radars for sensing bicyclists.

This data is combined with bus location data and information on traffic signal phases to identify potentially dangerous interactions. The city has a few months of data and is still figuring out how to use it.

“We are currently working with Verizon to ensure that the data being collected by the sensors is reliable and can be displayed visually in a way that is useful for planners and engineers here,” said Vineet Gupta, director of planning at the Boston Transportation Department. “They can give us information about the speed of oncoming vehicles approaching the intersection, or they can give us data on near-misses… It’s those kinds of subtleties that will help us get a good understanding of the intersection.”

So far, the data is being used to assess red-light running and encroachment by drivers into the bike lane, Woyke writes. Eventually, the city hopes to expand the sensor program to six additional intersections along Massachusetts Avenue.

On the other side of the country, in Bellevue, Washington, an effort is underway to use existing traffic cameras — no additional sensors required — to measure intersection dangers. The city has partnered with Microsoft and the University of Washington to feed visuals from its traffic cameras into an algorithm that can tally the number and types of vehicles in an intersection, as well as their direction and speed, to identify collisions and near-misses. The project relies on volunteers to help the algorithm begin its machine learning — or as Doug Trumm at The Urbanist puts it, “unpaid labor benefiting one of the region’s largest corporations.”

Developing better tools to assess the threat of poor street design and bad driving may help fine-tune safety improvements or show why street redesigns are necessary, but what’s really in short supply isn’t information so much as political courage to implement changes, says Tom Fucoloro at Seattle Bike Blog:

We already know, for example, that a wide curb radius encourages people driving to take turns too quickly and too close to people walking. Each of the red areas [in the top image] above could be addressed by extending the curbs closer to the center of the intersection or by installing a protected intersection…

But will Bellevue (or any other city that uses this technology) have the guts to redesign their intersections to put the safety of people walking above the desire for quick turns? Hopefully this data can help convince leaders, but well see.

Advocates in Boston have been pushing the city to make the hard choices necessary to improve safety on its streets, as well, including at Massachusetts Avenue and Beacon Street, but have so far been disappointed at the pace of change.

There are some things you don’t need an algorithm to figure out.

  • John French

    Interesting that the “danger zones” in the graphic are shaped a lot like bulbouts. I’d be very interested to see a similar graphic for an intersection with bulbouts–do they remove the danger zones, or just move them?

  • AMH

    “…what’s really in short supply isn’t information so much as political courage to implement changes.”

    Exactly this–but perhaps having data will give encourage hesitant officials? Sort of like the consultant who comes in, studies the dysfunctional workgroup, and recommends the same changes that everyone knew all along needed to be made.

  • We could always just stop building these intersections that are known to be dangerous.

  • Looking at historic data of intersections that look the same. BadIntersections.com has a database of 11,000+ dangerous intersections. A good majority have the same characteristics. This is not brain surgery folks. Intersections are dangerous by design!!!

  • Ryan Peterson

    We should be able to enthusiastically throw our support behind this technology as well as good design principles. Good design isn’t going to get us to zero on its own. Could not this technology also be used to vary the length of pedestrian intervals based on demand or walk speeds of pedestrians already in the intersection? How about the ability to warn motorists or peds/cyclists of the presence of other users or the likelihood of an impending collision or even slow or stop a vehicle that is on a trajectory to collide with a ped/cyclist?

    At the very least the technology will be able to help us directly measure exposure rates –
    something we can really only do by proxy right now. These are just a few potential benefits and there are probably others that haven’t been thought of yet.

    Also, one of the criticisms of artificial intelligence and machine learning is that it is too often biased by those helping to program/train it. The crowd sourcing effort could be beneficial in providing more diverse inputs.

    Finally, this technology is built to take advantage of existing infrastructure. Cash strapped local agencies could use the help.

ALSO ON STREETSBLOG

Four Cities Race to Finish the Country’s First Protected Intersection

|
Michael Andersen blogs for The Green Lane Project, a PeopleForBikes program that helps U.S. cities build better bike lanes to create low-stress streets. Sometimes, change builds up for years. And sometimes, it bursts. Fifteen months after American bikeway designer Nick Falbo coined the phrase “protected intersection” to refer to a Dutch-style intersection between two streets […]

There’s No Doubt: Traffic Enforcement Cameras Save Lives

|
Gawker dished out some richly-deserved ridicule to Tennessee State Senator Jon Lundberg yesterday, following reports that he is co-sponsoring legislation to outlaw the specific speeding camera that nabbed him doing 60 in a 45 zone last October. Lundberg denied that the incident had any impact on his decision to sponsor in the legislation, and contested the […]

Crashes Doubled After Houston Banned Red Light Cameras

|
Law enforcement officers warned there would likely be an uptick in collisions when Houston debated banning red light cameras in the early part of the decade. Turns out they were absolutely right. Houston voters banned the life-saving technology in 2010, with the press mostly cheering them along. Last year Houston PD examined how that’s impacted safety at intersections. According […]

Can a New Way to Measure Streets Help Advocates Tame Speeding?

|
You’ve heard of sensors that can count cars or bikes. Tools like that can help transportation planners make smarter decisions about where bike infrastructure is needed, for example. A new digital tool called Placemeter aims to measure streets at a much more fine-grained level, analyzing a variety of different aspects of movement in an urban environment. […]