Tech Tuesday: How AI Could Shorten Your Commute

early morning city traffic before sunrise
early morning city traffic before sunrise

 big-idea-logo.jpg

If you live in the Washington D.C. Metro Area you are well aware of the constant challenge of the morning commute. You are looking at a parking lot masquerading as an Interstate, and the constant slog of the bumper-to-bumper progress from home to job. There is that mindset of “taking a backway” but there you face an entirely different challenge of the traffic light. You drive a few feet, feel like you’re making progress, and then all of a sudden you hit a red light. Then another down the ways is green, but the next one in another few blocks is red. There seems to be no real pattern to it because, to tell the truth, there isn’t. The lights are out of sequence either to a backlog of maintenance, those who miss the trigger for the timer, or those who manage to sneak through a yellow light. The worse they are out of sequence, the more cars back up.

Wouldn’t it be nice if an eye in the sky could look down and organize all of these lights to maximize traffic flow? What an amazing system it would be. We’re talking about a management system that could dynamically adjust traffic flow instead of relying on fixed clocks and pressure sensitive timers.

Such a system is in the works, and it is a system that is built around Artifical intelligence. So while A.I. has often been prophesied as enslaving mankind, currently it is trying to help shorten the morning commute.

Commuting.The startup Surtrac has been upgrading traffic light controls in Pittsburgh with an Artificial Intelligence program with the end goal to lighten up morning commutes across the city, and then eventually offer similar systems to larger urban areas. How Surtrac lights and their A.I. works is by collecting data on the amount of traffic from cameras and radar signals. The network of lights work as independent operators, coordinating with each other to ensure that all traffic passes through intersections as fast as possible, setting their timing dynamically. The system is decentralized, meaning each light is only responsible for its own intersection, then coordinates with other signals by sending information on incoming cars. This reduces the data load on the network, and Surtrac also plans to enable their system to communicate directly with cars. Such a system could notify drivers of traffic conditions in advance through dashboard or smartphone apps. This A.I. system could also prioritize certain types of traffic, such as emergency vehicles.

Surtrac’s AI system began with nine intersections in Pittsburgh’s East Liberty neighborhood in 2012, and has quietly expanded to 50 intersections. The startup plans to implement their network across the whole city, and is expected to take this technology to other cities around the country. Just in Pittsburgh alone, Surtrac signals have reduced travel time for drivers by 25%, and time spent idling in traffic by 40%, reducing emissions by 21%.

This is, most assuredly, a good sign.

Unfortunately, there isn’t a definitive deadline for when AI traffic lights will be exported outside of Pittsburgh to other U.S. cities. But with the advent of self-driving cars quickly approaching, chances that it’ll be sooner than later.

 

 


 

shurtz.jpgA research physicist who has become an entrepreneur and educational leader, and an expert on competency-based education, critical thinking in the classroom, curriculum development, and education management, Dr. Richard Shurtz is the president and chief executive officer of Stratfdord University. He has published over 30 technical publications, holds 15 patents, and is host of the weekly radio show, Tech Talk. A noted expert on competency-based education, Dr. Shurtz has conducted numerous workshops and seminars for educators in Jamaica, Egypt, India, and China, and has established academic partnerships in China, India, Sri Lanka, Kurdistan, Malaysia, and Canada.

 

 

Leave a Reply

Your email address will not be published. Required fields are marked *