AI: AI solves traffic problems to get you where you’re going safely

“I’ve never met anyone who really likes traffic,” says Karina Rex of the FTA.

Probably with the exception of specialists like her who were tasked with reducing it.

Rex has made her career out of paying attention to traffic patterns. Prior to her current role as Associate Research, Innovation and Demonstration Officer for the FTA, she was the Director of Mobility and Infrastructure for the City of Pittsburgh, Pennsylvania. She’s spent countless hours thinking about cars, public transportation, roads, and pedestrians — and how to make it all flow more smoothly.

“When you’re at peak travel times, when the system is so full, it only takes a little downtime to make really big problems,” says Rex. “The job is to quickly report these disruptions and quickly retool the system to work around them.”

What Rex aims to improve affects anyone moving from point A to point B, especially in cities. She explained that congestion is the number one problem when it comes to traffic, which is common in urban areas. Add to that the number of variables at any given time, including human operators for vehicles and geography, and it results in a mind boggling puzzle even trying to solve.

She said that if there was an easy way to reduce traffic, it would have been implemented in the past 50 years. Instead, they are government organizations and startups in the space, such as I wishThey all look at the vast amount of available traffic data — from traffic sensors to ride-sharing data to bike and scooter data from smartphones — and use it to inform decisions about how to get people to work, home and grocery store safely and quickly.

This solution includes artificial intelligence and machine learning.

“There are tasks that humans are not good at in those machines, and that is pattern recognition,” explains Tim Maynard, founder and CEO of Lyt, a software technology platform that provides mobility solutions for cities. “Artificial intelligence is a great technology to use, because you look at all parts of the system. You can start giving them different information, and you can put that into a system that can make operational changes.”

Maynard started Lyt after studying intelligent transportation systems for more than 13 years. His company uses vehicle data to solve traffic problems, especially when it comes to the efficiency of public transportation options. For Maynard, the ultimate goal is to “make more cities more equitable by making public transportation reliable, predictable, and faster.”

Rex and Menard believe the way to reduce traffic is to get more people into public transportation, such as buses, subways, and light rail systems. Public transportation is the safest form of surface transportation, with fewer injuries and deaths. It is also a faster way to move more people.

Rex explained that most of the congestion is caused by “low volume vehicles,” ie. Single passenger cars. These drivers are human. Some drive faster, others slower; Some lanes change more often, others stop abruptly when the traffic light flashes yellow before red. Since humans behave very differently, there is a level of unpredictability in the traffic system. Much of her work aims to make mass transit more attractive to passengers.

“You reduce the rate of accidents that can happen when you reduce the number of vehicles there,” Rex added.

With this in mind, Maynard began researching the Internet of Things for his cloud platform, pulling data from smartphones, car sensors, transit logs, and delivery vehicles to understand traffic patterns at different times of the day as well as during special-out events, such as a game Sports in a local stadium. The first hurdle, he said, is to work from the place of known information rather than guesswork. In the past, he explained, it would have taken a human to look at a video screen for hours upon hours to begin to make an estimate of the next steps.

Launched in San Jose, California, over the past three years it has collaborated with the city to improve bus routes by 20%, thereby reducing fuel consumption by 14% and emissions at intersections by 12%. Using a predictive estimated time of arrival at each traffic light, his platform reduced travel time between bus stops by optimizing bus lanes and traffic lights to ensure buses can move as efficiently as possible without disrupting other traffic. It now operates in other Northern California cities, including additional Bay Area towns and Sacramento, as well as in the Pacific Northwest: Seattle and Portland, Oregon.

Maynard is also looking at bike and pedestrian traffic, something he says is of importance and priority for many transportation authorities. He’s made cycling safer by creating bike lanes with their own traffic lights synchronized with vehicle traffic lights to help avoid car and bike collisions. For pedestrians, Rex explained, foot traffic uses adaptive sensors and controls to adjust settings in real time based on needs — the moment an AI algorithm intersects with real-time data.

Another benefit of AI technology is the traffic patterns surrounding first responders. Maynard used machine learning to analyze data from emergency vehicles such as ambulances and fire trucks to improve speed. He noted that in many urban environments, congestion and traffic patterns prevent first responders from having immediate access to the scene of an accident or to a life-or-death hospital. In Sacramento, California, he addressed this problem.

“Night and day literally got better in less than 15 minutes,” he said of taking a look at the data collected from all relevant stakeholders in the city. There, he improved the slowest 10% of emergency vehicles at more than 10 miles per hour, allowing them to reach 70% faster at any response. Even the top 10% of cars saw an improvement of 6 mph.

For every one passenger car that converts to public transportation, there is less vehicle on the road causing congestion. Menard regularly reminds people that when they are sitting in their car, stuck in traffic, they are surrounded by many other people who are doing the exact same thing. If they trade in for a shared vehicle – a high-occupancy mode of transportation – they may speed along the road very quickly.

But it is always difficult to inspire passengers to change their habits, so the new option must be compelling enough to motivate them to modify the way they work. “What you want in the transportation system is to appear now [and] “There’s a bus ready to pick you up just in time,” Rex said. “We need to tackle the traffic so that transit is that attractive alternative. There is still a lot of work to be done.”

Leave a Comment