Researchers at the National Institute of Technology (NIT) Rourkela have patented a pioneering AI model designed to enhance road safety by improving communication between vehicles in Vehicular Ad-Hoc Networks (VANETs).
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, Prof. Bibhudatta Sahoo, and Dr. Lopamudra Hota from the Department of Computer Science & Engineering.
VANETs allow vehicles in close proximity to exchange real-time data, enabling features like electronic brake lights, emergency alerts, and traffic updates. However, simultaneous data transmission from multiple vehicles often leads to congestion and message loss. The NIT Rourkela team’s AI model solves this by using multi-agent deep reinforcement learning, allowing vehicles to intelligently stagger message timing and prioritize critical alerts.
Dr. Arun Kumar emphasized the urgency of such innovations, citing India’s 2023 road accident statistics: over 480,000 incidents and 172,000 fatalities. “Our work is a step toward building safer roads and smarter cities,” he said, aligning the project with the Innovate in India and Make in India missions.
The model’s applications extend beyond safety. It supports platooning, electronic toll collection, on-the-go retail payments, and smart city infrastructure, making it a cornerstone for future autonomous vehicle systems.
Prof. Bibhudatta Sahoo added, “This patent lays the groundwork for coordinated, congestion-free vehicle communication. We invite researchers to collaborate and accelerate India’s journey toward intelligent transportation.”
