Every year Texas highways collect several metric tons of road debris, a problem that endangers drivers and stalls traffic.
At high speed, even small tire debris can cause sudden vehicle swirls and secondary crashes and miles of traffic backups, said Yan Huang, a professor of computer science and engineering at the University of North Texas.
The debris not only creates immediate hazards but also initiates chain reactions, leading to secondary crashes that further congest already busy roads.
Right now, TxDOT doesn’t know about debris on roads unless it’s reported by someone.
“You do it after the incident happens and even stays there for some time, causing chain reactions, secondary crashes,” Huang explained.
To address this, Huang and her colleague Heng Fan are partnering with TxDOT to develop an artificial intelligence system that quickly spots road debris and alerts crews.
They plan to combine several data streams, including reports from the WAZE app, to detect dangers in real-time.
“We’ve seen that roughly 72% of debris reports come from WAZE, and those reports tend to be received about 16 minutes earlier than traditional methods,” Huang said in a November press release.
By combining WAZE with other crowdsourced data, they hope to detect debris even faster and improve response times.
The system will also utilize TxDOT closed-circuit cameras and data from connected vehicles and dash cameras, which are becoming more widely available.
“We’re integrating a multiple source of data, including crowd-sourced data and the connected vehicles, dash camera data, which is more and more available,” she said.
Fan emphasized that the system won’t retain personal information such as human faces or vehicle license plate numbers.
“So, that means that always the AI system will be safe to detect the debris only,” Fan said.
Huang noted that the Texas A&M Transportation Institute also reached out to be a partner on this project.
They hope to launch a prototype next year, driven by one mission.
“On busy highways, minutes really save lives. So, this is the goal of our project,” Huang said.
## Key Takeaways
– Several metric tons of debris accumulate on Texas highways each year.
– Roughly 72% of debris reports come from the WAZE app, arriving about 16 minutes earlier than traditional methods.
– The AI system will integrate WAZE data, closed-circuit cameras, connected vehicles, and dash camera feeds while protecting personal privacy.
The partnership between UNT researchers, TxDOT, and Texas A&M Transportation Institute aims to deploy a prototype next year, with the ultimate goal of reducing secondary crashes and saving lives on busy Texas highways.
