A research team from Johns Hopkins won a Best Paper Award at the IEEE Future Networks World Forum 2025 conference, held in Bangalore, India, in November. The winning paper, “Seeing More With Less: Leveraging Positional Telemetry for V2X Cooperative Perception,” presents a novel algorithm that improves vehicular perception in vehicle-to-everything (V2X) networks. These networks enable vehicles to communicate wirelessly with objects, such as traffic lights and other vehicles.

“This paper represents a significant step forward in enhancing vehicular situational awareness by enabling the efficient sharing of sensor information over limited V2X channels,” said Krishan Sabnani, a professor of computer science and co-founder of the S4 Lab, whose goal is to build safe and reliable systems for connected transportation. “The results have the potential to greatly improve road safety and move autonomous driving closer to true Level 5 performance. This achievement also marks the first major success emerging from our S4 Lab.”

The researchers explain that there are often challenges when implementing traditional fusion methods, as these networks have limited bandwidth available for data transmission. To address this, they developed a new system that relies on raw-level telemetry data that is automatically collected from remote systems and devices. The new system increased the precision of detection by more than 21 percent, and the methodology provides stronger results compared to other fusion algorithms.

Authors of the paper include Sabnani; Shenghua Chen, a PhD student in the Department of Computer Science; and Anton Dahbura, an associate research professor of computer science and co-director of the Johns Hopkins Institute for Assured Autonomy—as well as Ilya Sabnani of Saliynt and Manzoor A. Khan and Ilija Hadzic of Nokia Bell Labs.

“Our work provides foundational support for systems related to cooperative perception, autonomous driving, and safety-critical maneuvering by enabling robust data fusion,” the researchers write in their paper.

In the future, the team plans to advance its fusion technique and evaluate its system in real-world scenarios to ensure that the system performs as strongly as expected.