Researchers at the National Institute of Technology (NIT) Rourkela have patented an AI model designed to improve vehicle-to-vehicle communication for making roads safer.
The patent, titled “Adaptive Contention Window Optimisation in VANETs using Multi-Agent Deep Reinforcement Learning for Enhanced Performance Model”, was filed by Dr Arun Kumar, assistant professor; Prof Bibhudatta Sahoo, Dr Lopamudra Hota, research graduate, from the department of computer science & engineering.
The model addresses a key challenge in Vehicular Ad-Hoc Networks (VANETs) — when multiple vehicles send messages simultaneously, congestion can delay or block crucial alerts. The AI-driven system uses multi-agent deep reinforcement learning to sequence communications, ensuring that time-sensitive messages, such as sudden braking alerts or emergency notifications, reach other vehicles without delay.
“In 2023, India reported around 480,000 road accidents and 172,000 deaths, many of which could be prevented using modern technologies. Our work is a step towards building safer roads and smarter cities,” Kumar said.
Sahoo added, “The patent represents a practical move toward vehicle-to-vehicle communication in India. By reducing congestion in VANETs, the model lays the groundwork for safer and more efficient traffic management. We invite researchers across institutions to collaborate with our lab on autonomous vehicle technologies.”
Potential applications of the technology include electronic brake lights, platooning, real-time traffic updates, emergency alerts, and on-the-move services such as restaurant or toll information. Experts say VANETs could also support future smart city systems by enabling autonomous vehicles to coordinate in real time.
