Fahimeh Aghaei

The advent of 6G and beyond aims to redefine industrial automation by enabling seamless communication and intelligent systems. Among key verticals, mobile machinery applications such as autonomous vehicles and robotic systems face challenges like unreliable communication in complex environments, high latency, and insufficient spectrum resources.

Problem:
These issues limit the deployment of real-time systems essential for dynamic operations.

The research question focuses on:
How can accurate channel modelling and advanced communication technologies empower mobile machinery applications in 6G and beyond?

Our research emphasis on channel modelling to address propagation challenges in dynamic and multipath-rich environments. By integrating ray tracing techniques, the research provides precise simulation of wave propagation, capturing reflections, diffraction, and scattering in complex industrial settings. Physics-Informed Neural Networks (PINNs) are utilized to fuse propagation physics with machine learning, enabling predictive modelling of channel characteristics under varying environmental conditions.
These methodologies are validated through hybrid simulations, real-world experiments, and adaptive system prototyping.

Potential benefits:
Improved Network Reliability: Accurate channel models enable robust system designs.
Optimized Propagation: Ray tracing and PINNs enhance connectivity in challenging environments.

Scalable Solutions: Beyond-6G technologies adapt to diverse industrial needs, fostering advancements in IoT and autonomous systems.

By prioritizing channel modelling, this research bridges critical gaps in mobile machinery connectivity, driving efficiency and innovation in 6G-powered verticals.