How artificial intelligence is being used to help reduce crashes


The AI studies cars, pedestrians, and bicyclists with their activity, including locations, lane, speed and acceleration. — Photo by Nabeel Syed on Unsplash

Some roadways in Florida are becoming a testing ground for artificial intelligence to help find solutions to prevent crashes.

In a leap forward toward safety, Broward County is using the University of Florida’s artificial intelligence (AI)-based algorithms to track cars, bicyclists and pedestrians by camera. As part of a pilot program, researchers are analysing how to avoid collisions before they even happen – and using AI to help surface some solutions.

Broward is the latest community in the state to use this new approach. Pilot programs also have taken place in Gainesville and Seminole County.

Before, researchers had to see when a “crash happened and afterwards we have to look at information to determine the cause, what kind of safety solution may be helpful,” said Min-Tang Li, spokesman for Broward’s Traffic Engineering Division. But this new approach “will allow us to be more proactive – to identify potential crashes – and also gives us a better picture how things happen.”

Six intersections along Stirling Road in Broward are being examined for the number of times crashes nearly happened there, “because traffic intersections are prone to crashes leading to injury or fatality,” according to a research report.

An analysis

The technology studies video data from traffic intersections to understand where “near misses” – but not actual accidents – are happening.

That can include what time of day most near-accidents happen, and whether there are more issues with drivers making left turns or right turns, said University of Florida professor Sanjay Ranka. “The overall goal is use of these near-misses” to have fewer accidents “and obviously less fatalities,” he said.

The AI studies cars, pedestrians, and bicyclists with their activity, including locations, lane, speed and acceleration, Min-Tang Li said.

Relying on witnesses in the past only gave a limited sense of what happened. That kind of insight can be misguided because there are factors that influence facts, such as where the witness was standing, Li said.

“We can’t get the whole picture, more objective information is difficult to obtain,” Li said.

Ranka said one outcome from the Gainesville study was realising that pedestrians needed more time to cross one particular intersection near a high school. But doing that would slow down car traffic. The final suggestion was to increase the pedestrian crossing time, but only in the afternoons during peak pedestrian hours. “There was no point in making changes throughout the day,” he said.

Thanks to the program in Broward, some changes already have occurred, such as new signs reminding drivers to stop for pedestrians. The final analysis won’t be ready until at least June. The program is expected to be expanded elsewhere in the county, officials said. – South Florida Sun-Sentinel/Tribune News Service

Follow us on our official WhatsApp channel for breaking news alerts and key updates!

Next In Tech News

Thoma Bravo-backed SailPoint valued at $12.8 billion in stock market return
Arm secures Meta as first customer for ambitious new chip project, FT reports
Ubisoft reports 52% drop in Q3 net bookings, in line with guidance
Siemens shareholders reject proposal to allow virtual AGMs
Europe set to see record data centre capacity roll-out in 2025, CBRE says
Mexico could file suit against Google for 'Gulf of Mexico' name change
Meta to show rival ads providers on Marketplace after EU antitrust fine
Indian state officials seek to solve worker dispute at Samsung plant
Datadog sees annual revenue, profit below estimates as enterprise spending lags
Apptronik raises $350 million to scale production of humanoid robots

Others Also Read