NIT Rourkela Researchers Patent AI Model to Boost Road Safety Through Smarter Vehicle Communication

Researchers of the National Institute of Technology (NIT) Rourkela have patented a cutting-edge artificial intelligence model designed to improve car-to-car communication in future transportation systems, a significant step towards safer and smarter roads.

The patented model, officially titled “Adaptive Contention Window Optimisation in VANETs using Multi-Agent Deep Reinforcement Learning for Enhanced Performance Model”, has been developed by Dr. Arun Kumar, Assistant Professor; Prof. Bibhudatta Sahoo, Professor; and Dr. Lopamudra Hota, Research Graduate from the Department of Computer Science & Engineering at NIT Rourkela.

Tackling Communication Congestion in VANETs
The team’s work addresses a persistent challenge in Vehicular Ad-Hoc Networks (VANETs) — congestion caused when multiple vehicles send messages simultaneously. Such congestion can delay or block critical alerts, undermining the effectiveness of systems designed to prevent accidents and improve traffic flow.

Using multi-agent deep reinforcement learning, the AI model enables vehicles to intelligently stagger and prioritise communication. This ensures that high-priority alerts, such as sudden braking or accident notifications, are transmitted without delay — even in high-traffic scenarios.

Dr. Arun Kumar said, “In 2023, India reported around 480,000 road accidents and 172,000 deaths, many of which could be prevented with modern technologies.” He further added, “Our work is a step towards building safer roads and smarter cities. We envision a near future where autonomous vehicles become a reality in India, and this patent is a small step in that direction.”

Potential Applications in Smart Mobility
The technology could power several future applications:

• Electronic brake lights that warn drivers of hazards beyond their direct line of sight

• Platooning, where multiple vehicles move in coordination by sharing acceleration and steering data

• Real-time traffic updates for better navigation and congestion management

• Emergency alerts to support faster response from rescue teams

• On-the-road services, including electronic toll collection, local retail payments, and restaurant suggestions

Prof. Bibhudatta Sahoo emphasized the broader vision: “This patent is a practical step towards preparing India’s road system for vehicle-to-vehicle communication. By addressing potential congestion in VANETs, we’re laying the groundwork for safer and more efficient traffic management.”

Towards Smarter, Safer Cities
The patented system ensures that critical information reaches the right vehicle at the right time, strengthening the foundation for autonomous driving and smart city infrastructure in India.

Researchers at NIT Rourkela are inviting collaboration from institutions and industry to further refine and deploy the technology in real-world scenarios.